{"task":"Instance Segmentation","dataset":"COCO minival","metric_names":["mask AP","AP50","AP75","APL","APM","APS","GFLOPs","Params (M)"],"rows":[{"id":85617,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Co-DETR","metrics":{"AP50":"79.7","AP75":"62.8","APL":"74.6","APM":"59.7","APS":"38.9","mask AP":"56.6"},"paper_url":"https://arxiv.org/abs/2211.12860v5","paper_title":"DETRs with Collaborative Hybrid Assignments Training","paper_date":"2022-11-22","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85618,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ViT-CoMer-L (Mask RCNN, DINOv2)","metrics":{"mask AP":"55.9"},"paper_url":"https://openreview.net/forum?id=srPMwpkWbR&invitationId=thecvf.com/CVPR/2024/Conference/Submission1221/-/Camera_Ready_Revision&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3Dthecvf.com%2FCVPR%2F2024%2FConference%2FAuthors%23author-tasks)","paper_title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","paper_date":"2024-03-13","code_links":[{"title":"Traffic-X/ViT-CoMer","url":"https://github.com/Traffic-X/ViT-CoMer"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85619,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"InternImage-H","metrics":{"AP50":"80.1","AP75":"61.5","APL":"74.4","APM":"58.4","APS":"37.9","mask AP":"55.4"},"paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_date":"2022-11-10","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85620,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"EVA","metrics":{"AP50":"79.4","AP75":"60.9","APL":"72.0","APM":"58.4","APS":"37.6","mask AP":"55.0"},"paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","paper_date":"2022-11-14","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmselfsup","url":"https://github.com/open-mmlab/mmselfsup"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/beit"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85621,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask Frozen-DETR","metrics":{"AP50":"78.9","AP75":"60.8","APL":"72.9","APM":"58.4 ","APS":"37.2","mask AP":"54.9"},"paper_url":"https://arxiv.org/abs/2308.03747v1","paper_title":"Mask Frozen-DETR: High Quality Instance Segmentation with One GPU","paper_date":"2023-08-07","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85622,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MasK DINO (SwinL, multi-scale)","metrics":{"mask AP":"54.5"},"paper_url":"https://arxiv.org/abs/2206.02777v3","paper_title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","paper_date":"2022-06-06","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"IDEACVR/DINO","url":"https://github.com/IDEACVR/DINO"},{"title":"idea-research/maskdino","url":"https://github.com/idea-research/maskdino"},{"title":"idea-research/dn-detr","url":"https://github.com/idea-research/dn-detr"},{"title":"IDEA-opensource/DN-DETR","url":"https://github.com/IDEA-opensource/DN-DETR"},{"title":"IDEA-opensource/DAB-DETR","url":"https://github.com/IDEA-opensource/DAB-DETR"},{"title":"idea-research/dab-detr","url":"https://github.com/idea-research/dab-detr"},{"title":"isbrycee/gem-glass-segmentor","url":"https://github.com/isbrycee/gem-glass-segmentor"},{"title":"isbrycee/gem","url":"https://github.com/isbrycee/gem"},{"title":"Expedit-LargeScale-Vision-Transformer/Expedit-DINO","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85623,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)","metrics":{"mask AP":"54.2"},"paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","paper_date":"2022-05-17","code_links":[{"title":"czczup/vit-adapter","url":"https://github.com/czczup/vit-adapter"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85624,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"GLEE-Pro","metrics":{"mask AP":"54.2"},"paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","paper_date":"2023-12-14","code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85625,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"SwinV2-G (HTC++)","metrics":{"mask AP":"53.7"},"paper_url":"https://arxiv.org/abs/2111.09883v2","paper_title":"Swin Transformer V2: Scaling Up Capacity and Resolution","paper_date":"2021-11-18","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"microsoft/Swin-Transformer","url":"https://github.com/microsoft/Swin-Transformer"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/swin_transformer_v2"},{"title":"shinya7y/UniverseNet","url":"https://github.com/shinya7y/UniverseNet"},{"title":"lucidrains/flash-cosine-sim-attention","url":"https://github.com/lucidrains/flash-cosine-sim-attention"},{"title":"ChristophReich1996/Swin-Transformer-V2","url":"https://github.com/ChristophReich1996/Swin-Transformer-V2"},{"title":"impiga/plain-detr","url":"https://github.com/impiga/plain-detr"},{"title":"rami0205/ngramswin","url":"https://github.com/rami0205/ngramswin"},{"title":"isaaccorley/hydro-foundation-model","url":"https://github.com/isaaccorley/hydro-foundation-model"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2","url":"https://github.com/nku-shengzheliu/PaddlePaddle-Swin-Transformer-V2"},{"title":"shkarupa-alex/tfswin","url":"https://github.com/shkarupa-alex/tfswin"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/swin_transformer_v2.py"},{"title":"Burf/SwinTransformer-Tensorflow2","url":"https://github.com/Burf/SwinTransformer-Tensorflow2"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Qdriving/Swin-TransformerV2-in-PP","url":"https://github.com/Qdriving/Swin-TransformerV2-in-PP"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/swin"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/swin"},{"title":"lyqcom/aaic_swintransformerv2","url":"https://github.com/lyqcom/aaic_swintransformerv2"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/swin"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85626,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ViTDet, ViT-H Cascade (multiscale)","metrics":{"mask AP":"53.1"},"paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","paper_date":"2022-03-30","code_links":[{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/vitdet"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"ViTAE-Transformer/ViTDet","url":"https://github.com/ViTAE-Transformer/ViTDet"},{"title":"vitae-transformer/qformer","url":"https://github.com/vitae-transformer/qformer"},{"title":"kdexd/coco-rem","url":"https://github.com/kdexd/coco-rem"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"hula-ai/DAMA","url":"https://github.com/hula-ai/DAMA"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/vitdet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/vitdet"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/vit"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85627,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"GLEE-Plus","metrics":{"mask AP":"53.0"},"paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","paper_date":"2023-12-14","code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85628,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask DINO (SwinL)","metrics":{"mask AP":"52.6"},"paper_url":"https://arxiv.org/abs/2206.02777v3","paper_title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","paper_date":"2022-06-06","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"IDEACVR/DINO","url":"https://github.com/IDEACVR/DINO"},{"title":"idea-research/maskdino","url":"https://github.com/idea-research/maskdino"},{"title":"idea-research/dn-detr","url":"https://github.com/idea-research/dn-detr"},{"title":"IDEA-opensource/DN-DETR","url":"https://github.com/IDEA-opensource/DN-DETR"},{"title":"IDEA-opensource/DAB-DETR","url":"https://github.com/IDEA-opensource/DAB-DETR"},{"title":"idea-research/dab-detr","url":"https://github.com/idea-research/dab-detr"},{"title":"isbrycee/gem-glass-segmentor","url":"https://github.com/isbrycee/gem-glass-segmentor"},{"title":"isbrycee/gem","url":"https://github.com/isbrycee/gem"},{"title":"Expedit-LargeScale-Vision-Transformer/Expedit-DINO","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85629,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Soft Teacher + Swin-L(HTC++, multi-scale)","metrics":{"mask AP":"52.5"},"paper_url":"https://arxiv.org/abs/2106.09018v3","paper_title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","paper_date":"2021-06-16","code_links":[{"title":"microsoft/SoftTeacher","url":"https://github.com/microsoft/SoftTeacher"},{"title":"amazon-science/bigdetection","url":"https://github.com/amazon-science/bigdetection"},{"title":"amazon-research/bigdetection","url":"https://github.com/amazon-research/bigdetection"},{"title":"hikvision-research/SSOD","url":"https://github.com/hikvision-research/SSOD"},{"title":"JCZ404/Semi-DETR","url":"https://github.com/JCZ404/Semi-DETR"},{"title":"lexisnexis-risk-open-source/ledetection","url":"https://github.com/lexisnexis-risk-open-source/ledetection"},{"title":"hattrickcr7/SoftTeacher","url":"https://github.com/hattrickcr7/SoftTeacher"},{"title":"hik-lab/ssod","url":"https://github.com/hik-lab/ssod"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85630,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ViT-Adapter-L (HTC++, BEiTv2 pretrain, multi-scale)","metrics":{"mask AP":"52.5"},"paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","paper_date":"2022-05-17","code_links":[{"title":"czczup/vit-adapter","url":"https://github.com/czczup/vit-adapter"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85631,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ViT-Adapter-L (HTC++, BEiT pretrain, multi-scale)","metrics":{"mask AP":"52.2"},"paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","paper_date":"2022-05-17","code_links":[{"title":"czczup/vit-adapter","url":"https://github.com/czczup/vit-adapter"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85632,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ViTDet, ViT-H Cascade","metrics":{"mask AP":"52"},"paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","paper_date":"2022-03-30","code_links":[{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/vitdet"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"ViTAE-Transformer/ViTDet","url":"https://github.com/ViTAE-Transformer/ViTDet"},{"title":"vitae-transformer/qformer","url":"https://github.com/vitae-transformer/qformer"},{"title":"kdexd/coco-rem","url":"https://github.com/kdexd/coco-rem"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"hula-ai/DAMA","url":"https://github.com/hula-ai/DAMA"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/vitdet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/vitdet"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/vit"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85633,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Soft Teacher + Swin-L(HTC++, single-scale)","metrics":{"mask AP":"51.9"},"paper_url":"https://arxiv.org/abs/2106.09018v3","paper_title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","paper_date":"2021-06-16","code_links":[{"title":"microsoft/SoftTeacher","url":"https://github.com/microsoft/SoftTeacher"},{"title":"amazon-science/bigdetection","url":"https://github.com/amazon-science/bigdetection"},{"title":"amazon-research/bigdetection","url":"https://github.com/amazon-research/bigdetection"},{"title":"hikvision-research/SSOD","url":"https://github.com/hikvision-research/SSOD"},{"title":"JCZ404/Semi-DETR","url":"https://github.com/JCZ404/Semi-DETR"},{"title":"lexisnexis-risk-open-source/ledetection","url":"https://github.com/lexisnexis-risk-open-source/ledetection"},{"title":"hattrickcr7/SoftTeacher","url":"https://github.com/hattrickcr7/SoftTeacher"},{"title":"hik-lab/ssod","url":"https://github.com/hik-lab/ssod"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85634,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"mask AP":"51.8"},"paper_url":"https://arxiv.org/abs/2107.00420v7","paper_title":"CBNet: A Composite Backbone Network Architecture for Object Detection","paper_date":"2021-07-01","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"shinya7y/UniverseNet","url":"https://github.com/shinya7y/UniverseNet"},{"title":"VDIGPKU/CBNetV2","url":"https://github.com/VDIGPKU/CBNetV2"},{"title":"epsilon-deltta/epsilon-deltta","url":"https://github.com/epsilon-deltta/epsilon-deltta"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85635,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Frozen Backbone, SwinV2-G-ext22K (HTC)","metrics":{"mask AP":"51.6"},"paper_url":"https://arxiv.org/abs/2211.02043v1","paper_title":"Could Giant Pretrained Image Models Extract Universal Representations?","paper_date":"2022-11-03","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85636,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"mask AP":"51"},"paper_url":"https://arxiv.org/abs/2107.00420v7","paper_title":"CBNet: A Composite Backbone Network Architecture for Object Detection","paper_date":"2021-07-01","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"shinya7y/UniverseNet","url":"https://github.com/shinya7y/UniverseNet"},{"title":"VDIGPKU/CBNetV2","url":"https://github.com/VDIGPKU/CBNetV2"},{"title":"epsilon-deltta/epsilon-deltta","url":"https://github.com/epsilon-deltta/epsilon-deltta"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85637,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Focal-L (HTC++, multi-scale)","metrics":{"mask AP":"50.9"},"paper_url":"https://arxiv.org/abs/2107.00641v1","paper_title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","paper_date":"2021-07-01","code_links":[{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/Focal_Transformer"},{"title":"microsoft/Focal-Transformer","url":"https://github.com/microsoft/Focal-Transformer"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85638,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"DiNAT-L (single-scale, Mask2Former)","metrics":{"AP50":"75.0","mask AP":"50.8"},"paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","paper_date":"2022-09-29","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/Neighborhood-Attention-Transformer","url":"https://github.com/SHI-Labs/Neighborhood-Attention-Transformer"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/nat"},{"title":"shi-labs/natten","url":"https://github.com/shi-labs/natten"},{"title":"alexmehta/nac-tcn-tcns-with-causal-na","url":"https://github.com/alexmehta/nac-tcn-tcns-with-causal-na"},{"title":"MindSpore-scientific/code-8","url":"https://github.com/MindSpore-scientific/code-8/tree/main/MicAugment"},{"title":"MindSpore-scientific/code-10","url":"https://github.com/MindSpore-scientific/code-10/tree/main/MicAugment"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85639,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MViTv2-L (Cascade Mask R-CNN, multi-scale, IN21k pre-train)","metrics":{"mask AP":"50.5"},"paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","paper_date":"2021-12-02","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/main/projects/MViTv2"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"facebookresearch/mvit","url":"https://github.com/facebookresearch/mvit"},{"title":"JunweiLiang/aicity_action","url":"https://github.com/JunweiLiang/aicity_action"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"rajatmodi62/occludedactionbenchmark","url":"https://github.com/rajatmodi62/occludedactionbenchmark"},{"title":"3dperceptionlab/visual-wetlandbirds","url":"https://github.com/3dperceptionlab/visual-wetlandbirds"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85640,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Swin-L (HTC++, multi scale)","metrics":{"mask AP":"50.4"},"paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","paper_date":"2021-03-25","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"pytorch/vision","url":"https://github.com/pytorch/vision"},{"title":"microsoft/Swin-Transformer","url":"https://github.com/microsoft/Swin-Transformer"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"layumi/Person_reID_baseline_pytorch","url":"https://github.com/layumi/Person_reID_baseline_pytorch"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/swin_transformers.py"},{"title":"mzeromiko/vmamba","url":"https://github.com/mzeromiko/vmamba"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"facebookresearch/hiera","url":"https://github.com/facebookresearch/hiera"},{"title":"berniwal/swin-transformer-pytorch","url":"https://github.com/berniwal/swin-transformer-pytorch"},{"title":"SwinTransformer/Transformer-SSL","url":"https://github.com/SwinTransformer/Transformer-SSL"},{"title":"shinya7y/UniverseNet","url":"https://github.com/shinya7y/UniverseNet"},{"title":"AntixK/PyTorch-Model-Compare","url":"https://github.com/AntixK/PyTorch-Model-Compare"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"martinsbruveris/tensorflow-image-models","url":"https://github.com/martinsbruveris/tensorflow-image-models"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"},{"title":"LiWentomng/OrientedRepPoints","url":"https://github.com/LiWentomng/OrientedRepPoints"},{"title":"rishigami/Swin-Transformer-TF","url":"https://github.com/rishigami/Swin-Transformer-TF"},{"title":"mindspore-ecosystem/mindcv","url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/swin_transformer.py"},{"title":"xiaohu2015/swint_detectron2","url":"https://github.com/xiaohu2015/swint_detectron2"},{"title":"SforAiDl/vformer","url":"https://github.com/SforAiDl/vformer"},{"title":"DarshanDeshpande/jax-models","url":"https://github.com/DarshanDeshpande/jax-models"},{"title":"PaddlePaddle/PLSC","url":"https://github.com/PaddlePaddle/PLSC/tree/master/task/classification/swin"},{"title":"yingkaisha/keras-vision-transformer","url":"https://github.com/yingkaisha/keras-vision-transformer"},{"title":"YongWookHa/swin-transformer-ocr","url":"https://github.com/YongWookHa/swin-transformer-ocr"},{"title":"WangFeng18/Swin-Transformer","url":"https://github.com/WangFeng18/Swin-Transformer"},{"title":"rami0205/ngramswin","url":"https://github.com/rami0205/ngramswin"},{"title":"yangyangxu0/demt","url":"https://github.com/yangyangxu0/demt"},{"title":"ayanglab/swinmr","url":"https://github.com/ayanglab/swinmr"},{"title":"VcampSoldiers/Swin-Transformer-Tensorflow","url":"https://github.com/VcampSoldiers/Swin-Transformer-Tensorflow"},{"title":"sayakpaul/swin-transformers-tf","url":"https://github.com/sayakpaul/swin-transformers-tf"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"koechslin/swin-transformer-semantic-segmentation","url":"https://github.com/koechslin/swin-transformer-semantic-segmentation"},{"title":"HzcIrving/DeepLearning_PlayGround","url":"https://github.com/HzcIrving/DeepLearning_PlayGround/tree/main/Swin-Transformer"},{"title":"abman23/pmnet","url":"https://github.com/abman23/pmnet"},{"title":"innat/HybridModel-GradCAM","url":"https://github.com/innat/HybridModel-GradCAM"},{"title":"innat/VideoSwin","url":"https://github.com/innat/VideoSwin"},{"title":"megvii-research/basecls","url":"https://github.com/megvii-research/basecls/tree/main/zoo/public/swin"},{"title":"shkarupa-alex/tfswin","url":"https://github.com/shkarupa-alex/tfswin"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"mujiyantosvc/Facial-Expression-Recognition-FER-for-Mental-Health-Detection-","url":"https://github.com/mujiyantosvc/Facial-Expression-Recognition-FER-for-Mental-Health-Detection-"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/swin_transformer.py"},{"title":"ayanglab/swinganmr","url":"https://github.com/ayanglab/swinganmr"},{"title":"JIA-HONG-CHU/Swin-Transformer-add-EncNet-DaNet-DraNet-for-semantic-segmentation-on-Statelite-Dataset","url":"https://github.com/JIA-HONG-CHU/Swin-Transformer-add-EncNet-DaNet-DraNet-for-semantic-segmentation-on-Statelite-Dataset"},{"title":"Burf/SwinTransformer-Tensorflow2","url":"https://github.com/Burf/SwinTransformer-Tensorflow2"},{"title":"weiwang31/icemamba","url":"https://github.com/weiwang31/icemamba"},{"title":"USTC-IMCL/HST-for-Compressed-SR","url":"https://github.com/USTC-IMCL/HST-for-Compressed-SR"},{"title":"ustc-imcl/hst-for-compressed-image-sr","url":"https://github.com/ustc-imcl/hst-for-compressed-image-sr"},{"title":"IMvision12/keras-vision-models","url":"https://github.com/IMvision12/keras-vision-models"},{"title":"jahongir7174/MaskRCNN","url":"https://github.com/jahongir7174/MaskRCNN"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/swintransformer"},{"title":"shellredia/snake-swin-octa","url":"https://github.com/shellredia/snake-swin-octa"},{"title":"NEUdeep/Swin-Transformer-Object-Detection","url":"https://github.com/NEUdeep/Swin-Transformer-Object-Detection"},{"title":"zhangbo2008/swin-transformer_noted_very_detail","url":"https://github.com/zhangbo2008/swin-transformer_noted_very_detail"},{"title":"DominickZhang/Distillation-Swin-Transformer","url":"https://github.com/DominickZhang/Distillation-Swin-Transformer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/swin"},{"title":"holdfire/FAS","url":"https://github.com/holdfire/FAS"},{"title":"holdfire/CLS","url":"https://github.com/holdfire/CLS"},{"title":"MindCode-4/code-7","url":"https://github.com/MindCode-4/code-7/tree/main/isr"},{"title":"nathanlem1/igae-net","url":"https://github.com/nathanlem1/igae-net"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/SwinTransformer"},{"title":"lyqcom/aaic_swintransformerv2","url":"https://github.com/lyqcom/aaic_swintransformerv2"},{"title":"fogfog2/packnet","url":"https://github.com/fogfog2/packnet"},{"title":"liuxingwt/CLS","url":"https://github.com/liuxingwt/CLS"},{"title":"Mind23-2/MindCode-165","url":"https://github.com/Mind23-2/MindCode-165"},{"title":"Mind23-2/MindCode-155","url":"https://github.com/Mind23-2/MindCode-155"},{"title":"befallenStar/molecularAtt","url":"https://github.com/befallenStar/molecularAtt"},{"title":"Mind23-2/MindCode-117","url":"https://github.com/Mind23-2/MindCode-117"},{"title":"canerozer/qct","url":"https://github.com/canerozer/qct"},{"title":"Gojay001/toolkit-DeepLearning","url":"https://github.com/Gojay001/toolkit-DeepLearning"},{"title":"Myyyr/transseg2d","url":"https://github.com/Myyyr/transseg2d"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85641,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MOAT-3 (IN-22K pretraining, single-scale)","metrics":{"mask AP":"50.3"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85642,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask2Former (Swin-L)","metrics":{"mask AP":"50.1"},"paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","paper_date":"2021-12-02","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/Mask2Former","url":"https://github.com/facebookresearch/Mask2Former"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"nihalsid/mask2former","url":"https://github.com/nihalsid/mask2former"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/Mask2Former"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85643,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Swin-L (HTC++, single scale)","metrics":{"mask AP":"49.5"},"paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","paper_date":"2021-03-25","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"pytorch/vision","url":"https://github.com/pytorch/vision"},{"title":"microsoft/Swin-Transformer","url":"https://github.com/microsoft/Swin-Transformer"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"layumi/Person_reID_baseline_pytorch","url":"https://github.com/layumi/Person_reID_baseline_pytorch"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/vision/swin_transformers.py"},{"title":"mzeromiko/vmamba","url":"https://github.com/mzeromiko/vmamba"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"facebookresearch/hiera","url":"https://github.com/facebookresearch/hiera"},{"title":"berniwal/swin-transformer-pytorch","url":"https://github.com/berniwal/swin-transformer-pytorch"},{"title":"SwinTransformer/Transformer-SSL","url":"https://github.com/SwinTransformer/Transformer-SSL"},{"title":"shinya7y/UniverseNet","url":"https://github.com/shinya7y/UniverseNet"},{"title":"AntixK/PyTorch-Model-Compare","url":"https://github.com/AntixK/PyTorch-Model-Compare"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"martinsbruveris/tensorflow-image-models","url":"https://github.com/martinsbruveris/tensorflow-image-models"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"},{"title":"LiWentomng/OrientedRepPoints","url":"https://github.com/LiWentomng/OrientedRepPoints"},{"title":"rishigami/Swin-Transformer-TF","url":"https://github.com/rishigami/Swin-Transformer-TF"},{"title":"mindspore-ecosystem/mindcv","url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/swin_transformer.py"},{"title":"xiaohu2015/swint_detectron2","url":"https://github.com/xiaohu2015/swint_detectron2"},{"title":"SforAiDl/vformer","url":"https://github.com/SforAiDl/vformer"},{"title":"DarshanDeshpande/jax-models","url":"https://github.com/DarshanDeshpande/jax-models"},{"title":"PaddlePaddle/PLSC","url":"https://github.com/PaddlePaddle/PLSC/tree/master/task/classification/swin"},{"title":"yingkaisha/keras-vision-transformer","url":"https://github.com/yingkaisha/keras-vision-transformer"},{"title":"YongWookHa/swin-transformer-ocr","url":"https://github.com/YongWookHa/swin-transformer-ocr"},{"title":"WangFeng18/Swin-Transformer","url":"https://github.com/WangFeng18/Swin-Transformer"},{"title":"rami0205/ngramswin","url":"https://github.com/rami0205/ngramswin"},{"title":"yangyangxu0/demt","url":"https://github.com/yangyangxu0/demt"},{"title":"ayanglab/swinmr","url":"https://github.com/ayanglab/swinmr"},{"title":"VcampSoldiers/Swin-Transformer-Tensorflow","url":"https://github.com/VcampSoldiers/Swin-Transformer-Tensorflow"},{"title":"sayakpaul/swin-transformers-tf","url":"https://github.com/sayakpaul/swin-transformers-tf"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"koechslin/swin-transformer-semantic-segmentation","url":"https://github.com/koechslin/swin-transformer-semantic-segmentation"},{"title":"HzcIrving/DeepLearning_PlayGround","url":"https://github.com/HzcIrving/DeepLearning_PlayGround/tree/main/Swin-Transformer"},{"title":"abman23/pmnet","url":"https://github.com/abman23/pmnet"},{"title":"innat/HybridModel-GradCAM","url":"https://github.com/innat/HybridModel-GradCAM"},{"title":"innat/VideoSwin","url":"https://github.com/innat/VideoSwin"},{"title":"megvii-research/basecls","url":"https://github.com/megvii-research/basecls/tree/main/zoo/public/swin"},{"title":"shkarupa-alex/tfswin","url":"https://github.com/shkarupa-alex/tfswin"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"mujiyantosvc/Facial-Expression-Recognition-FER-for-Mental-Health-Detection-","url":"https://github.com/mujiyantosvc/Facial-Expression-Recognition-FER-for-Mental-Health-Detection-"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/swin_transformer.py"},{"title":"ayanglab/swinganmr","url":"https://github.com/ayanglab/swinganmr"},{"title":"JIA-HONG-CHU/Swin-Transformer-add-EncNet-DaNet-DraNet-for-semantic-segmentation-on-Statelite-Dataset","url":"https://github.com/JIA-HONG-CHU/Swin-Transformer-add-EncNet-DaNet-DraNet-for-semantic-segmentation-on-Statelite-Dataset"},{"title":"Burf/SwinTransformer-Tensorflow2","url":"https://github.com/Burf/SwinTransformer-Tensorflow2"},{"title":"weiwang31/icemamba","url":"https://github.com/weiwang31/icemamba"},{"title":"USTC-IMCL/HST-for-Compressed-SR","url":"https://github.com/USTC-IMCL/HST-for-Compressed-SR"},{"title":"ustc-imcl/hst-for-compressed-image-sr","url":"https://github.com/ustc-imcl/hst-for-compressed-image-sr"},{"title":"IMvision12/keras-vision-models","url":"https://github.com/IMvision12/keras-vision-models"},{"title":"jahongir7174/MaskRCNN","url":"https://github.com/jahongir7174/MaskRCNN"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/swintransformer"},{"title":"shellredia/snake-swin-octa","url":"https://github.com/shellredia/snake-swin-octa"},{"title":"NEUdeep/Swin-Transformer-Object-Detection","url":"https://github.com/NEUdeep/Swin-Transformer-Object-Detection"},{"title":"zhangbo2008/swin-transformer_noted_very_detail","url":"https://github.com/zhangbo2008/swin-transformer_noted_very_detail"},{"title":"DominickZhang/Distillation-Swin-Transformer","url":"https://github.com/DominickZhang/Distillation-Swin-Transformer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/swin"},{"title":"holdfire/FAS","url":"https://github.com/holdfire/FAS"},{"title":"holdfire/CLS","url":"https://github.com/holdfire/CLS"},{"title":"MindCode-4/code-7","url":"https://github.com/MindCode-4/code-7/tree/main/isr"},{"title":"nathanlem1/igae-net","url":"https://github.com/nathanlem1/igae-net"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/SwinTransformer"},{"title":"lyqcom/aaic_swintransformerv2","url":"https://github.com/lyqcom/aaic_swintransformerv2"},{"title":"fogfog2/packnet","url":"https://github.com/fogfog2/packnet"},{"title":"liuxingwt/CLS","url":"https://github.com/liuxingwt/CLS"},{"title":"Mind23-2/MindCode-165","url":"https://github.com/Mind23-2/MindCode-165"},{"title":"Mind23-2/MindCode-155","url":"https://github.com/Mind23-2/MindCode-155"},{"title":"befallenStar/molecularAtt","url":"https://github.com/befallenStar/molecularAtt"},{"title":"Mind23-2/MindCode-117","url":"https://github.com/Mind23-2/MindCode-117"},{"title":"canerozer/qct","url":"https://github.com/canerozer/qct"},{"title":"Gojay001/toolkit-DeepLearning","url":"https://github.com/Gojay001/toolkit-DeepLearning"},{"title":"Myyyr/transseg2d","url":"https://github.com/Myyyr/transseg2d"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85644,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MOAT-2 (IN-22K pretraining, single-scale)","metrics":{"mask AP":"49.3"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85645,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MOAT-1 (IN-1K pretraining, single-scale)","metrics":{"mask AP":"49.0"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85646,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"QueryInst (single scale)","metrics":{"AP50":"74.0","AP75":"53.9","APL":"68.3","APM":"52.6","APS":"30.8","mask AP":"48.9"},"paper_url":"https://arxiv.org/abs/2105.01928v3","paper_title":"Instances as Queries","paper_date":"2021-05-05","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"hustvl/QueryInst","url":"https://github.com/hustvl/QueryInst"},{"title":"Bo396543018/picodet_repro","url":"https://github.com/Bo396543018/picodet_repro"},{"title":"sty16/cell_mmdetection","url":"https://github.com/sty16/cell_mmdetection"},{"title":"flyfly666/mmdetection2.18.1","url":"https://github.com/flyfly666/mmdetection2.18.1"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85647,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)","metrics":{"mask AP":"48.9"},"paper_url":"https://arxiv.org/abs/2012.07177v2","paper_title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","paper_date":"2020-12-13","code_links":[{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"tensorflow/tpu","url":"https://github.com/tensorflow/tpu/tree/master/models/official/detection/projects/copy_paste"},{"title":"conradry/copy-paste-aug","url":"https://github.com/conradry/copy-paste-aug"},{"title":"RocketFlash/CAP_augmentation","url":"https://github.com/RocketFlash/CAP_augmentation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85648,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"InternImage-XL","metrics":{"GFLOPs":"1782","Params (M)":"387","mask AP":"48.8"},"paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_date":"2022-11-10","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85649,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)","metrics":{"mask AP":"48.8"},"paper_url":"https://arxiv.org/abs/2212.03863v2","paper_title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","paper_date":"2022-12-07","code_links":[{"title":"aim-uofa/DiverGen","url":"https://github.com/aim-uofa/DiverGen"},{"title":"yoctta/xpaste","url":"https://github.com/yoctta/xpaste"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85650,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Heira-L","metrics":{"mask AP":"48.6"},"paper_url":"https://arxiv.org/abs/2306.00989v1","paper_title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","paper_date":"2023-06-01","code_links":[{"title":"huggingface/pytorch-image-models","url":"https://github.com/huggingface/pytorch-image-models"},{"title":"facebookresearch/hiera","url":"https://github.com/facebookresearch/hiera"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/hiera"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85651,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"InternImage-L","metrics":{"GFLOPs":"1399","Params (M)":"277","box AP":"56.1","mask AP":"48.5"},"paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_date":"2022-11-10","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85652,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MViTv2-H (Cascade Mask R-CNN, single-scale, IN21k pre-train)","metrics":{"mask AP":"48.5"},"paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","paper_date":"2021-12-02","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/main/projects/MViTv2"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"facebookresearch/mvit","url":"https://github.com/facebookresearch/mvit"},{"title":"JunweiLiang/aicity_action","url":"https://github.com/JunweiLiang/aicity_action"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"rajatmodi62/occludedactionbenchmark","url":"https://github.com/rajatmodi62/occludedactionbenchmark"},{"title":"3dperceptionlab/visual-wetlandbirds","url":"https://github.com/3dperceptionlab/visual-wetlandbirds"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85653,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"GLEE-Lite","metrics":{"mask AP":"48.4"},"paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","paper_date":"2023-12-14","code_links":[{"title":"FoundationVision/GLEE","url":"https://github.com/FoundationVision/GLEE"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85654,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MOAT-0 (IN-1K pretraining, single-scale)","metrics":{"mask AP":"47.4"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85655,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MViTv2-L (Cascade Mask R-CNN, single-scale)","metrics":{"mask AP":"47.1"},"paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","paper_date":"2021-12-02","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/main/projects/MViTv2"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"facebookresearch/mvit","url":"https://github.com/facebookresearch/mvit"},{"title":"JunweiLiang/aicity_action","url":"https://github.com/JunweiLiang/aicity_action"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"rajatmodi62/occludedactionbenchmark","url":"https://github.com/rajatmodi62/occludedactionbenchmark"},{"title":"3dperceptionlab/visual-wetlandbirds","url":"https://github.com/3dperceptionlab/visual-wetlandbirds"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85656,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MPViT-B (Cascade Mask R-CNN, multi-scale, IN1k pre-train)","metrics":{"mask AP":"47.0"},"paper_url":"https://arxiv.org/abs/2112.11010v2","paper_title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","paper_date":"2021-12-21","code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"youngwanLEE/MPViT","url":"https://github.com/youngwanLEE/MPViT"},{"title":"DarshanDeshpande/jax-models","url":"https://github.com/DarshanDeshpande/jax-models"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85657,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"tiny-MOAT-3 (IN-1K pretraining, single-scale)","metrics":{"mask AP":"47.0"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85658,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Cascade Eff-B7 NAS-FPN (1280)","metrics":{"mask AP":"46.8"},"paper_url":"https://arxiv.org/abs/2012.07177v2","paper_title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","paper_date":"2020-12-13","code_links":[{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"tensorflow/tpu","url":"https://github.com/tensorflow/tpu/tree/master/models/official/detection/projects/copy_paste"},{"title":"conradry/copy-paste-aug","url":"https://github.com/conradry/copy-paste-aug"},{"title":"RocketFlash/CAP_augmentation","url":"https://github.com/RocketFlash/CAP_augmentation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85659,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ResNeSt-200 (multi-scale)","metrics":{"mask AP":"46.25"},"paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","paper_date":"2020-04-19","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"dmlc/gluon-cv","url":"https://github.com/dmlc/gluon-cv"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"zhanghang1989/ResNeSt","url":"https://github.com/zhanghang1989/ResNeSt"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"zhanghang1989/PyTorch-Encoding","url":"https://github.com/zhanghang1989/PyTorch-Encoding"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/resnest"},{"title":"chongruo/detectron2-resnest","url":"https://github.com/chongruo/detectron2-resnest"},{"title":"zhanghang1989/detectron2-ResNeSt","url":"https://github.com/zhanghang1989/detectron2-ResNeSt"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ResNeSt50"},{"title":"ZJCV/ZCls","url":"https://github.com/ZJCV/ZCls"},{"title":"Yuxiang1995/ICDAR2021_MFD","url":"https://github.com/Yuxiang1995/ICDAR2021_MFD"},{"title":"YeongHyeon/ResNeSt-TF2","url":"https://github.com/YeongHyeon/ResNeSt-TF2"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"Burf/ResNeSt-Tensorflow2","url":"https://github.com/Burf/ResNeSt-Tensorflow2"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"STomoya/ResNeSt","url":"https://github.com/STomoya/ResNeSt"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/resnest"},{"title":"shellhue/detectron2-ResNeSt","url":"https://github.com/shellhue/detectron2-ResNeSt"},{"title":"thepooons/melanoma-comp-2020","url":"https://github.com/thepooons/melanoma-comp-2020"},{"title":"AnudeepKonda/MIMII_anamoly_detection","url":"https://github.com/AnudeepKonda/MIMII_anamoly_detection"},{"title":"sailfish009/detectron2-ResNeSt","url":"https://github.com/sailfish009/detectron2-ResNeSt"},{"title":"ferna11i/detectron2_ResNeST","url":"https://github.com/ferna11i/detectron2_ResNeST"},{"title":"Asthestarsfalll/ResNeSt-MegEngine","url":"https://github.com/Asthestarsfalll/ResNeSt-MegEngine"},{"title":"Mind23-2/MindCode-115","url":"https://github.com/Mind23-2/MindCode-115"},{"title":"ChengWeiGu/ResNeSt-Pytorch","url":"https://github.com/ChengWeiGu/ResNeSt-Pytorch"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ResNeSt50"},{"title":"2023-MindSpore-4/Code6","url":"https://github.com/2023-MindSpore-4/Code6/tree/main/ResNeSt50"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ResNeSt50"},{"title":"mohitktanwr/Deep-Stem-ResNeSt-ISPRS","url":"https://github.com/mohitktanwr/Deep-Stem-ResNeSt-ISPRS"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/ResNeSt50"},{"title":"RobertHong1992/Resnest","url":"https://github.com/RobertHong1992/Resnest"},{"title":"He-jerry/DSSNet","url":"https://github.com/He-jerry/DSSNet"},{"title":"mohitktanwr/ResNeSt_Inverse","url":"https://github.com/mohitktanwr/ResNeSt_Inverse"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85660,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MViT-L (Mask R-CNN, single-scale)","metrics":{"mask AP":"46.2"},"paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","paper_date":"2021-12-02","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/main/projects/MViTv2"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"facebookresearch/mvit","url":"https://github.com/facebookresearch/mvit"},{"title":"JunweiLiang/aicity_action","url":"https://github.com/JunweiLiang/aicity_action"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"rajatmodi62/occludedactionbenchmark","url":"https://github.com/rajatmodi62/occludedactionbenchmark"},{"title":"3dperceptionlab/visual-wetlandbirds","url":"https://github.com/3dperceptionlab/visual-wetlandbirds"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85661,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"RetinaNet (SpineNet-190, 1536x1536)","metrics":{"mask AP":"46.1"},"paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","paper_date":"2019-12-10","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones"},{"title":"tensorflow/tpu","url":"https://github.com/tensorflow/tpu"},{"title":"tensorflow/tpu","url":"https://github.com/tensorflow/tpu/tree/master/models/official/detection"},{"title":"lucifer443/SpineNet-Pytorch","url":"https://github.com/lucifer443/SpineNet-Pytorch"},{"title":"yan-roo/SpineNet-Pytorch","url":"https://github.com/yan-roo/SpineNet-Pytorch"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/retinanet_resnet101"},{"title":"2023-MindSpore-4/Code9","url":"https://github.com/2023-MindSpore-4/Code9/tree/main/RetinaNet"},{"title":"2023-MindSpore-4/Code11","url":"https://github.com/2023-MindSpore-4/Code11/tree/main/retinanet_resnet152"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/retinanet_resnet152"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/retinanet_resnet101"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/SpineNet"},{"title":"MindSpore-paper-code-2/code3","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/ssd_resnet_34"},{"title":"code-implementation1/Code8","url":"https://github.com/code-implementation1/Code8/tree/main/SpineNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85662,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"MPViT-B (Cascade R-CNN, sinlge-scale, IN-1K pre-train)","metrics":{"mask AP":"45.8"},"paper_url":"https://arxiv.org/abs/2112.11010v2","paper_title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","paper_date":"2021-12-21","code_links":[{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"youngwanLEE/MPViT","url":"https://github.com/youngwanLEE/MPViT"},{"title":"DarshanDeshpande/jax-models","url":"https://github.com/DarshanDeshpande/jax-models"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85663,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ViL Base, multi-scale, 3x lr)","metrics":{"AP75":"49.9","mask AP":"45.7"},"paper_url":"https://arxiv.org/abs/2103.15358v2","paper_title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","paper_date":"2021-03-29","code_links":[{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/vision-longformer","url":"https://github.com/microsoft/vision-longformer"},{"title":"microsoft/VisionLongformerForObjectDetection","url":"https://github.com/microsoft/VisionLongformerForObjectDetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85664,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ViL Base, 1x lr)","metrics":{"AP50":"67.2","AP75":"49.3","mask AP":"45.1"},"paper_url":"https://arxiv.org/abs/2103.15358v2","paper_title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","paper_date":"2021-03-29","code_links":[{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/vision-longformer","url":"https://github.com/microsoft/vision-longformer"},{"title":"microsoft/VisionLongformerForObjectDetection","url":"https://github.com/microsoft/VisionLongformerForObjectDetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85665,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"tiny-MOAT-2 (IN-1K pretraining, single-scale)","metrics":{"mask AP":"45.0"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85666,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"GCNet (ResNeXt-101 + DCN + cascade + GC r4)","metrics":{"AP50":"67.9","AP75":"48.4","mask AP":"44.7"},"paper_url":"https://arxiv.org/abs/2012.13375v1","paper_title":"Global Context Networks","paper_date":"2020-12-24","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"xvjiarui/GCNet","url":"https://github.com/xvjiarui/GCNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85667,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"tiny-MOAT-1 (IN-1K pretraining, single-scale)","metrics":{"mask AP":"44.6"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85668,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"InternImage-S","metrics":{"GFLOPs":"340","Params (M)":"69","box AP":"49.7","mask AP":"44.5"},"paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_date":"2022-11-10","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85669,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ResNeSt-200-DCN (single-scale)","metrics":{"mask AP":"44.5"},"paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","paper_date":"2020-04-19","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"dmlc/gluon-cv","url":"https://github.com/dmlc/gluon-cv"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"zhanghang1989/ResNeSt","url":"https://github.com/zhanghang1989/ResNeSt"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"zhanghang1989/PyTorch-Encoding","url":"https://github.com/zhanghang1989/PyTorch-Encoding"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/resnest"},{"title":"chongruo/detectron2-resnest","url":"https://github.com/chongruo/detectron2-resnest"},{"title":"zhanghang1989/detectron2-ResNeSt","url":"https://github.com/zhanghang1989/detectron2-ResNeSt"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ResNeSt50"},{"title":"ZJCV/ZCls","url":"https://github.com/ZJCV/ZCls"},{"title":"Yuxiang1995/ICDAR2021_MFD","url":"https://github.com/Yuxiang1995/ICDAR2021_MFD"},{"title":"YeongHyeon/ResNeSt-TF2","url":"https://github.com/YeongHyeon/ResNeSt-TF2"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"Burf/ResNeSt-Tensorflow2","url":"https://github.com/Burf/ResNeSt-Tensorflow2"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"STomoya/ResNeSt","url":"https://github.com/STomoya/ResNeSt"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/resnest"},{"title":"shellhue/detectron2-ResNeSt","url":"https://github.com/shellhue/detectron2-ResNeSt"},{"title":"thepooons/melanoma-comp-2020","url":"https://github.com/thepooons/melanoma-comp-2020"},{"title":"AnudeepKonda/MIMII_anamoly_detection","url":"https://github.com/AnudeepKonda/MIMII_anamoly_detection"},{"title":"sailfish009/detectron2-ResNeSt","url":"https://github.com/sailfish009/detectron2-ResNeSt"},{"title":"ferna11i/detectron2_ResNeST","url":"https://github.com/ferna11i/detectron2_ResNeST"},{"title":"Asthestarsfalll/ResNeSt-MegEngine","url":"https://github.com/Asthestarsfalll/ResNeSt-MegEngine"},{"title":"Mind23-2/MindCode-115","url":"https://github.com/Mind23-2/MindCode-115"},{"title":"ChengWeiGu/ResNeSt-Pytorch","url":"https://github.com/ChengWeiGu/ResNeSt-Pytorch"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ResNeSt50"},{"title":"2023-MindSpore-4/Code6","url":"https://github.com/2023-MindSpore-4/Code6/tree/main/ResNeSt50"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ResNeSt50"},{"title":"mohitktanwr/Deep-Stem-ResNeSt-ISPRS","url":"https://github.com/mohitktanwr/Deep-Stem-ResNeSt-ISPRS"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/ResNeSt50"},{"title":"RobertHong1992/Resnest","url":"https://github.com/RobertHong1992/Resnest"},{"title":"He-jerry/DSSNet","url":"https://github.com/He-jerry/DSSNet"},{"title":"mohitktanwr/ResNeSt_Inverse","url":"https://github.com/mohitktanwr/ResNeSt_Inverse"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85670,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ELSA-S (Cascade Mask RCNN)","metrics":{"AP50":"67.8","AP75":"47.8","mask AP":"44.4"},"paper_url":"https://arxiv.org/abs/2112.12786v1","paper_title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","paper_date":"2021-12-23","code_links":[{"title":"damo-cv/elsa","url":"https://github.com/damo-cv/elsa"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85671,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"BoTNet 200 (Mask R-CNN, single scale, 72 epochs)","metrics":{"mask AP":"44.4"},"paper_url":"https://arxiv.org/abs/2101.11605v2","paper_title":"Bottleneck Transformers for Visual Recognition","paper_date":"2021-01-27","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT"},{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"lucidrains/bottleneck-transformer-pytorch","url":"https://github.com/lucidrains/bottleneck-transformer-pytorch"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/botnet"},{"title":"leaderj1001/BottleneckTransformers","url":"https://github.com/leaderj1001/BottleneckTransformers"},{"title":"BIGBALLON/distribuuuu","url":"https://github.com/BIGBALLON/distribuuuu"},{"title":"kevin-ssy/ViP","url":"https://github.com/kevin-ssy/ViP"},{"title":"CandiceD17/Bottleneck-Transformers-for-Visual-Recognition","url":"https://github.com/CandiceD17/Bottleneck-Transformers-for-Visual-Recognition"},{"title":"NZ99/bottleneck-transformer-flax","url":"https://github.com/NZ99/bottleneck-transformer-flax"},{"title":"MartinGer/Bottleneck-Transformers-for-Visual-Recognition","url":"https://github.com/MartinGer/Bottleneck-Transformers-for-Visual-Recognition"},{"title":"scheshmi/BottleneckTransformers","url":"https://github.com/scheshmi/BottleneckTransformers"},{"title":"nachiket273/VisTrans","url":"https://github.com/nachiket273/VisTrans"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85672,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"DaViT-T (Mask R-CNN, 36 epochs)","metrics":{"mask AP":"44.3"},"paper_url":"https://arxiv.org/abs/2204.03645v1","paper_title":"DaViT: Dual Attention Vision Transformers","paper_date":"2022-04-07","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/davit"},{"title":"dingmyu/davit","url":"https://github.com/dingmyu/davit"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85673,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ResNeSt-200 (single-scale)","metrics":{"mask AP":"44.21"},"paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","paper_date":"2020-04-19","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"dmlc/gluon-cv","url":"https://github.com/dmlc/gluon-cv"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"zhanghang1989/ResNeSt","url":"https://github.com/zhanghang1989/ResNeSt"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"zhanghang1989/PyTorch-Encoding","url":"https://github.com/zhanghang1989/PyTorch-Encoding"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/resnest"},{"title":"chongruo/detectron2-resnest","url":"https://github.com/chongruo/detectron2-resnest"},{"title":"zhanghang1989/detectron2-ResNeSt","url":"https://github.com/zhanghang1989/detectron2-ResNeSt"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ResNeSt50"},{"title":"ZJCV/ZCls","url":"https://github.com/ZJCV/ZCls"},{"title":"Yuxiang1995/ICDAR2021_MFD","url":"https://github.com/Yuxiang1995/ICDAR2021_MFD"},{"title":"YeongHyeon/ResNeSt-TF2","url":"https://github.com/YeongHyeon/ResNeSt-TF2"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"Burf/ResNeSt-Tensorflow2","url":"https://github.com/Burf/ResNeSt-Tensorflow2"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"STomoya/ResNeSt","url":"https://github.com/STomoya/ResNeSt"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/resnest"},{"title":"shellhue/detectron2-ResNeSt","url":"https://github.com/shellhue/detectron2-ResNeSt"},{"title":"thepooons/melanoma-comp-2020","url":"https://github.com/thepooons/melanoma-comp-2020"},{"title":"AnudeepKonda/MIMII_anamoly_detection","url":"https://github.com/AnudeepKonda/MIMII_anamoly_detection"},{"title":"sailfish009/detectron2-ResNeSt","url":"https://github.com/sailfish009/detectron2-ResNeSt"},{"title":"ferna11i/detectron2_ResNeST","url":"https://github.com/ferna11i/detectron2_ResNeST"},{"title":"Asthestarsfalll/ResNeSt-MegEngine","url":"https://github.com/Asthestarsfalll/ResNeSt-MegEngine"},{"title":"Mind23-2/MindCode-115","url":"https://github.com/Mind23-2/MindCode-115"},{"title":"ChengWeiGu/ResNeSt-Pytorch","url":"https://github.com/ChengWeiGu/ResNeSt-Pytorch"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ResNeSt50"},{"title":"2023-MindSpore-4/Code6","url":"https://github.com/2023-MindSpore-4/Code6/tree/main/ResNeSt50"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ResNeSt50"},{"title":"mohitktanwr/Deep-Stem-ResNeSt-ISPRS","url":"https://github.com/mohitktanwr/Deep-Stem-ResNeSt-ISPRS"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/ResNeSt50"},{"title":"RobertHong1992/Resnest","url":"https://github.com/RobertHong1992/Resnest"},{"title":"He-jerry/DSSNet","url":"https://github.com/He-jerry/DSSNet"},{"title":"mohitktanwr/ResNeSt_Inverse","url":"https://github.com/mohitktanwr/ResNeSt_Inverse"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85674,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"InternImage-T","metrics":{"GFLOPs":"270","Params (M)":"49","box AP":"49.1","mask AP":"43.7"},"paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_date":"2022-11-10","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85675,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"BoTNet 152 (Mask R-CNN, single scale, 72 epochs)","metrics":{"mask AP":"43.7"},"paper_url":"https://arxiv.org/abs/2101.11605v2","paper_title":"Bottleneck Transformers for Visual Recognition","paper_date":"2021-01-27","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT"},{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"lucidrains/bottleneck-transformer-pytorch","url":"https://github.com/lucidrains/bottleneck-transformer-pytorch"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/botnet"},{"title":"leaderj1001/BottleneckTransformers","url":"https://github.com/leaderj1001/BottleneckTransformers"},{"title":"BIGBALLON/distribuuuu","url":"https://github.com/BIGBALLON/distribuuuu"},{"title":"kevin-ssy/ViP","url":"https://github.com/kevin-ssy/ViP"},{"title":"CandiceD17/Bottleneck-Transformers-for-Visual-Recognition","url":"https://github.com/CandiceD17/Bottleneck-Transformers-for-Visual-Recognition"},{"title":"NZ99/bottleneck-transformer-flax","url":"https://github.com/NZ99/bottleneck-transformer-flax"},{"title":"MartinGer/Bottleneck-Transformers-for-Visual-Recognition","url":"https://github.com/MartinGer/Bottleneck-Transformers-for-Visual-Recognition"},{"title":"scheshmi/BottleneckTransformers","url":"https://github.com/scheshmi/BottleneckTransformers"},{"title":"nachiket273/VisTrans","url":"https://github.com/nachiket273/VisTrans"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85676,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"XCiT-M24/8","metrics":{"mask AP":"43.7"},"paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","paper_date":"2021-06-17","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"facebookresearch/dino","url":"https://github.com/facebookresearch/dino"},{"title":"facebookresearch/vissl","url":"https://github.com/facebookresearch/vissl"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/XCiT"},{"title":"facebookresearch/xcit","url":"https://github.com/facebookresearch/xcit"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/xcit"},{"title":"adrienangeli/dino","url":"https://github.com/adrienangeli/dino"},{"title":"BrilliantYuKaimin/XCiT-PaddlePaddle","url":"https://github.com/BrilliantYuKaimin/XCiT-PaddlePaddle"},{"title":"Mind23-2/MindCode-123","url":"https://github.com/Mind23-2/MindCode-123"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85677,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"tiny-MOAT-0 (IN-1K pretraining, single-scale)","metrics":{"mask AP":"43.3"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85678,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ELSA-S (Mask RCNN)","metrics":{"AP50":"67.3","AP75":"46.4","mask AP":"43.0"},"paper_url":"https://arxiv.org/abs/2112.12786v1","paper_title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","paper_date":"2021-12-23","code_links":[{"title":"damo-cv/elsa","url":"https://github.com/damo-cv/elsa"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85679,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"XCiT-S24/8","metrics":{"mask AP":"43.0"},"paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","paper_date":"2021-06-17","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"facebookresearch/dino","url":"https://github.com/facebookresearch/dino"},{"title":"facebookresearch/vissl","url":"https://github.com/facebookresearch/vissl"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/XCiT"},{"title":"facebookresearch/xcit","url":"https://github.com/facebookresearch/xcit"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/xcit"},{"title":"adrienangeli/dino","url":"https://github.com/adrienangeli/dino"},{"title":"BrilliantYuKaimin/XCiT-PaddlePaddle","url":"https://github.com/BrilliantYuKaimin/XCiT-PaddlePaddle"},{"title":"Mind23-2/MindCode-123","url":"https://github.com/Mind23-2/MindCode-123"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85680,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"CenterMask-VoVNetV2-99 (multi-scale)","metrics":{"mask AP":"42.5"},"paper_url":"https://arxiv.org/abs/1911.06667v6","paper_title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","paper_date":"2019-11-15","code_links":[{"title":"youngwanLEE/centermask2","url":"https://github.com/youngwanLEE/centermask2"},{"title":"youngwanLEE/CenterMask","url":"https://github.com/youngwanLEE/CenterMask"},{"title":"youngwanLEE/vovnet-detectron2","url":"https://github.com/youngwanLEE/vovnet-detectron2"},{"title":"zhuoyang125/CenterMask2","url":"https://github.com/zhuoyang125/CenterMask2"},{"title":"mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN","url":"https://github.com/mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN"},{"title":"mahdi-darvish/centermask","url":"https://github.com/mahdi-darvish/centermask"},{"title":"suvasis/birdnet2cs231n","url":"https://github.com/suvasis/birdnet2cs231n"},{"title":"hades12580/centermask2","url":"https://github.com/hades12580/centermask2"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85681,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"ResNeSt-101 (single-scale)","metrics":{"mask AP":"41.56"},"paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","paper_date":"2020-04-19","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"dmlc/gluon-cv","url":"https://github.com/dmlc/gluon-cv"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"zhanghang1989/ResNeSt","url":"https://github.com/zhanghang1989/ResNeSt"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"zhanghang1989/PyTorch-Encoding","url":"https://github.com/zhanghang1989/PyTorch-Encoding"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/resnest"},{"title":"chongruo/detectron2-resnest","url":"https://github.com/chongruo/detectron2-resnest"},{"title":"zhanghang1989/detectron2-ResNeSt","url":"https://github.com/zhanghang1989/detectron2-ResNeSt"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/ResNeSt50"},{"title":"ZJCV/ZCls","url":"https://github.com/ZJCV/ZCls"},{"title":"Yuxiang1995/ICDAR2021_MFD","url":"https://github.com/Yuxiang1995/ICDAR2021_MFD"},{"title":"YeongHyeon/ResNeSt-TF2","url":"https://github.com/YeongHyeon/ResNeSt-TF2"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"Burf/ResNeSt-Tensorflow2","url":"https://github.com/Burf/ResNeSt-Tensorflow2"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"STomoya/ResNeSt","url":"https://github.com/STomoya/ResNeSt"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/resnest"},{"title":"shellhue/detectron2-ResNeSt","url":"https://github.com/shellhue/detectron2-ResNeSt"},{"title":"thepooons/melanoma-comp-2020","url":"https://github.com/thepooons/melanoma-comp-2020"},{"title":"AnudeepKonda/MIMII_anamoly_detection","url":"https://github.com/AnudeepKonda/MIMII_anamoly_detection"},{"title":"sailfish009/detectron2-ResNeSt","url":"https://github.com/sailfish009/detectron2-ResNeSt"},{"title":"ferna11i/detectron2_ResNeST","url":"https://github.com/ferna11i/detectron2_ResNeST"},{"title":"Asthestarsfalll/ResNeSt-MegEngine","url":"https://github.com/Asthestarsfalll/ResNeSt-MegEngine"},{"title":"Mind23-2/MindCode-115","url":"https://github.com/Mind23-2/MindCode-115"},{"title":"ChengWeiGu/ResNeSt-Pytorch","url":"https://github.com/ChengWeiGu/ResNeSt-Pytorch"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ResNeSt50"},{"title":"2023-MindSpore-4/Code6","url":"https://github.com/2023-MindSpore-4/Code6/tree/main/ResNeSt50"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ResNeSt50"},{"title":"mohitktanwr/Deep-Stem-ResNeSt-ISPRS","url":"https://github.com/mohitktanwr/Deep-Stem-ResNeSt-ISPRS"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/ResNeSt50"},{"title":"RobertHong1992/Resnest","url":"https://github.com/RobertHong1992/Resnest"},{"title":"He-jerry/DSSNet","url":"https://github.com/He-jerry/DSSNet"},{"title":"mohitktanwr/ResNeSt_Inverse","url":"https://github.com/mohitktanwr/ResNeSt_Inverse"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85682,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"SIW","metrics":{"mask AP":"41.4"},"paper_url":"https://arxiv.org/abs/2202.02002v2","paper_title":"Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings","paper_date":"2022-02-04","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85683,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Res2Net-101+HTC","metrics":{"mask AP":"41.3"},"paper_url":"https://arxiv.org/abs/1904.01169v3","paper_title":"Res2Net: A New Multi-scale Backbone Architecture","paper_date":"2019-04-02","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"Res2Net/Res2Net-PretrainedModels","url":"https://github.com/Res2Net/Res2Net-PretrainedModels"},{"title":"gasvn/Res2Net","url":"https://github.com/gasvn/Res2Net"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/res2net"},{"title":"mindspore-ecosystem/mindcv","url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/res2net.py"},{"title":"Res2Net/Res2Net-maskrcnn","url":"https://github.com/Res2Net/Res2Net-maskrcnn"},{"title":"Res2Net/Res2Net-PoolNet","url":"https://github.com/Res2Net/Res2Net-PoolNet"},{"title":"Res2Net/mmdetection","url":"https://github.com/Res2Net/mmdetection"},{"title":"Res2Net/Res2Net-Pose-Estimation","url":"https://github.com/Res2Net/Res2Net-Pose-Estimation"},{"title":"zhuhongwei1999/bsa-net","url":"https://github.com/zhuhongwei1999/bsa-net"},{"title":"fupiao1998/res2net-keras","url":"https://github.com/fupiao1998/res2net-keras"},{"title":"ChrisMats/Res2Net","url":"https://github.com/ChrisMats/Res2Net"},{"title":"yfreedomliTHU/Res2Net","url":"https://github.com/yfreedomliTHU/Res2Net"},{"title":"IMvision12/keras-vision-models","url":"https://github.com/IMvision12/keras-vision-models"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/res2net"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/ResNeXt"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net_deeplabv3"},{"title":"tuanzhangCS/res2net-on-mxnet","url":"https://github.com/tuanzhangCS/res2net-on-mxnet"},{"title":"kingcong/res2net","url":"https://github.com/kingcong/res2net"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net_deeplabv3"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/res2net"},{"title":"MindSpore-scientific/code-14","url":"https://github.com/MindSpore-scientific/code-14/tree/main/res_mlp_ms"},{"title":"Mind23-2/MindCode-114","url":"https://github.com/Mind23-2/MindCode-114"},{"title":"yangyucheng000/res2net","url":"https://github.com/yangyucheng000/res2net/blob/main/res2net.py"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/res2net"},{"title":"MindSpore-paper-code-3/code5","url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/ResNeXt"},{"title":"MindSpore-paper-code-3/code5","url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/res2net_deeplabv3"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85684,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"HTC (HRNetV2p-W48)","metrics":{"mask AP":"41.0"},"paper_url":"http://arxiv.org/abs/1902.09212v1","paper_title":"Deep High-Resolution Representation Learning for Human Pose Estimation","paper_date":"2019-02-25","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"leoxiaobin/deep-high-resolution-net.pytorch","url":"https://github.com/leoxiaobin/deep-high-resolution-net.pytorch"},{"title":"HRNet/HRNet-Semantic-Segmentation","url":"https://github.com/HRNet/HRNet-Semantic-Segmentation"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"Microsoft/human-pose-estimation.pytorch","url":"https://github.com/Microsoft/human-pose-estimation.pytorch"},{"title":"HRNet/HRNet-Facial-Landmark-Detection","url":"https://github.com/HRNet/HRNet-Facial-Landmark-Detection"},{"title":"HRNet/HRNet-Image-Classification","url":"https://github.com/HRNet/HRNet-Image-Classification"},{"title":"HRNet/HRNet-Object-Detection","url":"https://github.com/HRNet/HRNet-Object-Detection"},{"title":"mindspore-lab/mindone","url":"https://github.com/mindspore-lab/mindone"},{"title":"leeyegy/SimDR","url":"https://github.com/leeyegy/SimDR"},{"title":"leeyegy/simcc","url":"https://github.com/leeyegy/simcc"},{"title":"mks0601/PoseFix_RELEASE","url":"https://github.com/mks0601/PoseFix_RELEASE"},{"title":"HRNet/HRNet-Human-Pose-Estimation","url":"https://github.com/HRNet/HRNet-Human-Pose-Estimation"},{"title":"strivebo/image_segmentation_dl","url":"https://github.com/strivebo/image_segmentation_dl"},{"title":"HRNet/HRNet-MaskRCNN-Benchmark","url":"https://github.com/HRNet/HRNet-MaskRCNN-Benchmark"},{"title":"CASIA-IVA-Lab/ISP-reID","url":"https://github.com/CASIA-IVA-Lab/ISP-reID"},{"title":"NVlabs/PAMTRI","url":"https://github.com/NVlabs/PAMTRI"},{"title":"k-miran/hear","url":"https://github.com/k-miran/hear"},{"title":"Vill-Lab/2022-TIP-HCGA","url":"https://github.com/Vill-Lab/2022-TIP-HCGA"},{"title":"d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification","url":"https://github.com/d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification"},{"title":"chuanqichen/deepcoaching","url":"https://github.com/chuanqichen/deepcoaching"},{"title":"Mary-xl/HRnet_Kaggle_iNat2019_FGVC","url":"https://github.com/Mary-xl/HRnet_Kaggle_iNat2019_FGVC"},{"title":"v1viswan/Domain_adaptation_in_HRNet","url":"https://github.com/v1viswan/Domain_adaptation_in_HRNet"},{"title":"ken724049/action-recognition","url":"https://github.com/ken724049/action-recognition"},{"title":"NU-LL/lighttrack-","url":"https://github.com/NU-LL/lighttrack-"},{"title":"thoughtmachines/Human-Pose-Estimation-using-HRNets","url":"https://github.com/thoughtmachines/Human-Pose-Estimation-using-HRNets"},{"title":"ducongju/HRNet","url":"https://github.com/ducongju/HRNet"},{"title":"thomasslloyd/FitSpatial","url":"https://github.com/thomasslloyd/FitSpatial"},{"title":"laowang666888/HRNET","url":"https://github.com/laowang666888/HRNET"},{"title":"baoshengyu/deep-high-resolution-net.pytorch","url":"https://github.com/baoshengyu/deep-high-resolution-net.pytorch"},{"title":"sdll/hrnet-pose-estimation","url":"https://github.com/sdll/hrnet-pose-estimation"},{"title":"gox-ai/hrnet-pose-api","url":"https://github.com/gox-ai/hrnet-pose-api"},{"title":"anshky/HR-NET","url":"https://github.com/anshky/HR-NET"},{"title":"wsjzha/deep-high-resolution-net.pytorch","url":"https://github.com/wsjzha/deep-high-resolution-net.pytorch"},{"title":"visionNoob/hrnet_pytorch","url":"https://github.com/visionNoob/hrnet_pytorch"},{"title":"abhi1kumar/hrnet_pose_single_gpu","url":"https://github.com/abhi1kumar/hrnet_pose_single_gpu"},{"title":"goutern/PoseEstimation","url":"https://github.com/goutern/PoseEstimation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85685,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"HTC (HRNetV2p-W48)","metrics":{"mask AP":"41.0"},"paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","paper_date":"2019-08-20","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"open-mmlab/mmsegmentation","url":"https://github.com/open-mmlab/mmsegmentation"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"CSAILVision/semantic-segmentation-pytorch","url":"https://github.com/CSAILVision/semantic-segmentation-pytorch"},{"title":"leoxiaobin/deep-high-resolution-net.pytorch","url":"https://github.com/leoxiaobin/deep-high-resolution-net.pytorch"},{"title":"HRNet/HRNet-Semantic-Segmentation","url":"https://github.com/HRNet/HRNet-Semantic-Segmentation"},{"title":"HRNet/HRNet-Facial-Landmark-Detection","url":"https://github.com/HRNet/HRNet-Facial-Landmark-Detection"},{"title":"HRNet/HRNet-Image-Classification","url":"https://github.com/HRNet/HRNet-Image-Classification"},{"title":"HRNet/HRNet-Object-Detection","url":"https://github.com/HRNet/HRNet-Object-Detection"},{"title":"mindspore-lab/mindone","url":"https://github.com/mindspore-lab/mindone"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/HRNetW48_cls"},{"title":"JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models","url":"https://github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models"},{"title":"mlpc-ucsd/PRTR","url":"https://github.com/mlpc-ucsd/PRTR"},{"title":"HRNet/HRNet-MaskRCNN-Benchmark","url":"https://github.com/HRNet/HRNet-MaskRCNN-Benchmark"},{"title":"yuanyuanli85/tf-hrnet","url":"https://github.com/yuanyuanli85/tf-hrnet"},{"title":"sithu31296/pose-estimation","url":"https://github.com/sithu31296/pose-estimation"},{"title":"megvii-research/basecls","url":"https://github.com/megvii-research/basecls/tree/main/zoo/public/hrnet"},{"title":"shuuchen/HRNet","url":"https://github.com/shuuchen/HRNet"},{"title":"pikabite/segmentations_tf2","url":"https://github.com/pikabite/segmentations_tf2"},{"title":"shijianjian/HRNet_Keras","url":"https://github.com/shijianjian/HRNet_Keras"},{"title":"d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification","url":"https://github.com/d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HRNetW48_cls"},{"title":"eshaanagarwal/hr-net-implementation","url":"https://github.com/eshaanagarwal/hr-net-implementation"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HRNetW48_cls"},{"title":"w-sugar/prtr","url":"https://github.com/w-sugar/prtr"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HMR"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HRNetW48_cls"},{"title":"Mind23-2/MindCode-4","url":"https://github.com/Mind23-2/MindCode-4/tree/main/hrnet"},{"title":"yukichou/PET","url":"https://github.com/yukichou/PET"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/HRNetW48_cls"},{"title":"alililia/ascend_HRNetW48_cls","url":"https://github.com/alililia/ascend_HRNetW48_cls"},{"title":"sdll/hrnet-pose-estimation","url":"https://github.com/sdll/hrnet-pose-estimation"},{"title":"2023-MindSpore-1/ms-code-162","url":"https://github.com/2023-MindSpore-1/ms-code-162"},{"title":"gox-ai/hrnet-pose-api","url":"https://github.com/gox-ai/hrnet-pose-api"},{"title":"anshky/HR-NET","url":"https://github.com/anshky/HR-NET"},{"title":"kingcong/gpu_HRNetW48_cls","url":"https://github.com/kingcong/gpu_HRNetW48_cls"},{"title":"yangyucheng000/HRNetW48_cls","url":"https://github.com/yangyucheng000/HRNetW48_cls"},{"title":"Calylyli/Mindsporehrnet","url":"https://github.com/Calylyli/Mindsporehrnet"},{"title":"baoshengyu/deep-high-resolution-net.pytorch","url":"https://github.com/baoshengyu/deep-high-resolution-net.pytorch"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85686,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"GCNet (ResNeXt-101 + DCN + cascade + GC r16)","metrics":{"mask AP":"40.9"},"paper_url":"http://arxiv.org/abs/1904.11492v1","paper_title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","paper_date":"2019-04-25","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmsegmentation","url":"https://github.com/open-mmlab/mmsegmentation"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"xvjiarui/GCNet","url":"https://github.com/xvjiarui/GCNet"},{"title":"Oichii/DeepPulse-pytorch","url":"https://github.com/Oichii/DeepPulse-pytorch"},{"title":"czero69/acomoeye-NN","url":"https://github.com/czero69/acomoeye-NN"},{"title":"xggIoU/GCNet_global_context_module_tensorflow","url":"https://github.com/xggIoU/GCNet_global_context_module_tensorflow"},{"title":"zhusiling/GCNet","url":"https://github.com/zhusiling/GCNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85687,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"BoTNet 50 (72 epochs)","metrics":{"mask AP":"40.7"},"paper_url":"https://arxiv.org/abs/2101.11605v2","paper_title":"Bottleneck Transformers for Visual Recognition","paper_date":"2021-01-27","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT"},{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"lucidrains/bottleneck-transformer-pytorch","url":"https://github.com/lucidrains/bottleneck-transformer-pytorch"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/botnet"},{"title":"leaderj1001/BottleneckTransformers","url":"https://github.com/leaderj1001/BottleneckTransformers"},{"title":"BIGBALLON/distribuuuu","url":"https://github.com/BIGBALLON/distribuuuu"},{"title":"kevin-ssy/ViP","url":"https://github.com/kevin-ssy/ViP"},{"title":"CandiceD17/Bottleneck-Transformers-for-Visual-Recognition","url":"https://github.com/CandiceD17/Bottleneck-Transformers-for-Visual-Recognition"},{"title":"NZ99/bottleneck-transformer-flax","url":"https://github.com/NZ99/bottleneck-transformer-flax"},{"title":"MartinGer/Bottleneck-Transformers-for-Visual-Recognition","url":"https://github.com/MartinGer/Bottleneck-Transformers-for-Visual-Recognition"},{"title":"scheshmi/BottleneckTransformers","url":"https://github.com/scheshmi/BottleneckTransformers"},{"title":"nachiket273/VisTrans","url":"https://github.com/nachiket273/VisTrans"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85688,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"R3-CNN (ResNet-50-FPN, DCN)","metrics":{"AP50":"61.3","AP75":"44","APL":"56.1","APM":"43.6","APS":"22.3","mask AP":"40.4"},"paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","paper_date":"2021-04-03","code_links":[{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85689,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ResNext-152, +1 NL)","metrics":{"mask AP":"40.3"},"paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","paper_date":"2017-11-21","code_links":[{"title":"facebookresearch/detectron","url":"https://github.com/facebookresearch/detectron"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"MIT-HAN-LAB/temporal-shift-module","url":"https://github.com/MIT-HAN-LAB/temporal-shift-module"},{"title":"facebookresearch/video-nonlocal-net","url":"https://github.com/facebookresearch/video-nonlocal-net"},{"title":"cmsflash/efficient-attention","url":"https://github.com/cmsflash/efficient-attention"},{"title":"tea1528/Non-Local-NN-Pytorch","url":"https://github.com/tea1528/Non-Local-NN-Pytorch"},{"title":"vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks","url":"https://github.com/vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks"},{"title":"franknb/Self-attention-DCGAN","url":"https://github.com/franknb/Self-attention-DCGAN"},{"title":"mirthai/csa-net","url":"https://github.com/mirthai/csa-net"},{"title":"tinymilky/RSANet","url":"https://github.com/tinymilky/RSANet"},{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"},{"title":"seominseok0429/inception-I3D-NON-LOCAL","url":"https://github.com/seominseok0429/inception-I3D-NON-LOCAL"},{"title":"jpviguerasguillen/feedback-non-local-attention-fnla","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention-fnla"},{"title":"JiaPeng1234/MRI-Segmentation-Transformer","url":"https://github.com/JiaPeng1234/MRI-Segmentation-Transformer"},{"title":"jpviguerasguillen/feedback-non-local-attention_fNLA","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention_fNLA"},{"title":"huyz1117/Non_Local_Net_TensorFlow","url":"https://github.com/huyz1117/Non_Local_Net_TensorFlow"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/Non_local"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/Non_local"},{"title":"WavesUR/embedded_TSM","url":"https://github.com/WavesUR/embedded_TSM"},{"title":"sunutf/TSM","url":"https://github.com/sunutf/TSM"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/I3D"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/Non_local"},{"title":"changliu816/CV-paper-review","url":"https://github.com/changliu816/CV-paper-review"},{"title":"jiajunhua/facebookresearch-Detectron","url":"https://github.com/jiajunhua/facebookresearch-Detectron"},{"title":"owena11/papers","url":"https://github.com/owena11/papers"},{"title":"LRacoci/permutation-graphml","url":"https://github.com/LRacoci/permutation-graphml"},{"title":"jordiae/DeepLearning-MAI","url":"https://github.com/jordiae/DeepLearning-MAI"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/Non_local"},{"title":"Aprilkaka/nonlocal_mindspore","url":"https://github.com/Aprilkaka/nonlocal_mindspore"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/Non_local"},{"title":"rijuldhir/TSM","url":"https://github.com/rijuldhir/TSM"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85690,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN-FPN (AOGNet-40M)","metrics":{"AP50":"63.2","AP75":"43.3","mask AP":"40.2"},"paper_url":"https://arxiv.org/abs/1908.01259v3","paper_title":"Attentive Normalization","paper_date":"2019-08-04","code_links":[{"title":"iVMCL/AOGNet-v2","url":"https://github.com/iVMCL/AOGNet-v2"},{"title":"ivMCL/AttentiveNorm_Detection","url":"https://github.com/ivMCL/AttentiveNorm_Detection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85691,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"R3-CNN (ResNet-50-FPN, GC-Net)","metrics":{"AP50":"61.1","AP75":"43.5","APM":"42.8","APS":"22.6","mask AP":"40.2"},"paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","paper_date":"2021-04-03","code_links":[{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85692,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"CenterMask-VoVNetV2-99-3x","metrics":{"mask AP":"40.2"},"paper_url":"https://arxiv.org/abs/1911.06667v6","paper_title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","paper_date":"2019-11-15","code_links":[{"title":"youngwanLEE/centermask2","url":"https://github.com/youngwanLEE/centermask2"},{"title":"youngwanLEE/CenterMask","url":"https://github.com/youngwanLEE/CenterMask"},{"title":"youngwanLEE/vovnet-detectron2","url":"https://github.com/youngwanLEE/vovnet-detectron2"},{"title":"zhuoyang125/CenterMask2","url":"https://github.com/zhuoyang125/CenterMask2"},{"title":"mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN","url":"https://github.com/mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN"},{"title":"mahdi-darvish/centermask","url":"https://github.com/mahdi-darvish/centermask"},{"title":"suvasis/birdnet2cs231n","url":"https://github.com/suvasis/birdnet2cs231n"},{"title":"hades12580/centermask2","url":"https://github.com/hades12580/centermask2"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85693,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"R3-CNN (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"58.8","AP75":"42.3","APL":"54.3","APM":"42.1","APS":"20.7","mask AP":"39.1"},"paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","paper_date":"2021-04-03","code_links":[{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85694,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask Scoring R-CNN (ResNet-101-FPN-DCN)","metrics":{"mask AP":"39.1"},"paper_url":"http://arxiv.org/abs/1903.00241v1","paper_title":"Mask Scoring R-CNN","paper_date":"2019-03-01","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"zjhuang22/maskscoring_rcnn","url":"https://github.com/zjhuang22/maskscoring_rcnn"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MTCNN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85695,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN-FPN (ResNeXt-101, GN+WS)","metrics":{"AP50":"61.07","AP75":"40.82","APL":"56.08","APM":"41.73","APS":"18.32","mask AP":"38.34"},"paper_url":"https://arxiv.org/abs/1903.10520v2","paper_title":"Micro-Batch Training with Batch-Channel Normalization and Weight Standardization","paper_date":"2019-03-25","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"joe-siyuan-qiao/WeightStandardization","url":"https://github.com/joe-siyuan-qiao/WeightStandardization"},{"title":"jinfagang/nb","url":"https://github.com/jinfagang/nb"},{"title":"delta6189/Anime-Sketch-Colorizer","url":"https://github.com/delta6189/Anime-Sketch-Colorizer"},{"title":"ThomasEhling/Weight_Standardization","url":"https://github.com/ThomasEhling/Weight_Standardization"},{"title":"lessw2020/auto-adaptive-ai","url":"https://github.com/lessw2020/auto-adaptive-ai"},{"title":"seujung/WeightStandardization_gluon","url":"https://github.com/seujung/WeightStandardization_gluon"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85696,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"R3-CNN (ResNet-50-FPN)","metrics":{"AP50":"58","AP75":"41.4","APL":"52.8","APM":"41","APS":"20.4","mask AP":"38.2"},"paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","paper_date":"2021-04-03","code_links":[{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85697,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"HTC (ResNet-50)","metrics":{"mask AP":"38.2"},"paper_url":"http://arxiv.org/abs/1901.07518v2","paper_title":"Hybrid Task Cascade for Instance Segmentation","paper_date":"2019-01-22","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"amirassov/kaggle-imaterialist","url":"https://github.com/amirassov/kaggle-imaterialist"},{"title":"zhaozhen2333/iflytek2021","url":"https://github.com/zhaozhen2333/iflytek2021"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85698,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask Scoring R-CNN (ResNet-101 FPN)","metrics":{"mask AP":"38.2"},"paper_url":"http://arxiv.org/abs/1903.00241v1","paper_title":"Mask Scoring R-CNN","paper_date":"2019-03-01","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"zjhuang22/maskscoring_rcnn","url":"https://github.com/zjhuang22/maskscoring_rcnn"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MTCNN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85699,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"PANet (ResNet-50)","metrics":{"mask AP":"37.8"},"paper_url":"http://arxiv.org/abs/1803.01534v4","paper_title":"Path Aggregation Network for Instance Segmentation","paper_date":"2018-03-05","code_links":[{"title":"ultralytics/yolov5","url":"https://github.com/ultralytics/yolov5"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"ShuLiu1993/PANet","url":"https://github.com/ShuLiu1993/PANet"},{"title":"texasinstruments/edgeai-yolov5","url":"https://github.com/texasinstruments/edgeai-yolov5"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/yolov5"},{"title":"texasinstruments/edgeai-yolox","url":"https://github.com/texasinstruments/edgeai-yolox"},{"title":"YuefeiZ/PANet","url":"https://github.com/YuefeiZ/PANet"},{"title":"CVUsers/Smart-Retail-By-Efficientdet","url":"https://github.com/CVUsers/Smart-Retail-By-Efficientdet"},{"title":"wslerry/yolov5","url":"https://github.com/wslerry/yolov5"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85700,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"GCnet (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"59.3","AP75":"39.8","APL":"51.2","APM":"41","APS":"20.2","mask AP":"37.2"},"paper_url":"https://arxiv.org/abs/2004.13665v2","paper_title":"A novel Region of Interest Extraction Layer for Instance Segmentation","paper_date":"2020-04-28","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/tree/master/configs/groie"},{"title":"IMPLabUniPr/mmdetection-groie","url":"https://github.com/IMPLabUniPr/mmdetection-groie"},{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"},{"title":"Gugan0905/steel-defect-detection","url":"https://github.com/Gugan0905/steel-defect-detection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85701,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (FPN, X-volution, SA)","metrics":{"APL":"53.1","APM":"40","APS":"19.2","mask AP":"37.2"},"paper_url":"https://arxiv.org/abs/2106.02253v2","paper_title":"X-volution: On the unification of convolution and self-attention","paper_date":"2021-06-04","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85702,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ResNet-101, +1 NL)","metrics":{"mask AP":"37.1"},"paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","paper_date":"2017-11-21","code_links":[{"title":"facebookresearch/detectron","url":"https://github.com/facebookresearch/detectron"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"MIT-HAN-LAB/temporal-shift-module","url":"https://github.com/MIT-HAN-LAB/temporal-shift-module"},{"title":"facebookresearch/video-nonlocal-net","url":"https://github.com/facebookresearch/video-nonlocal-net"},{"title":"cmsflash/efficient-attention","url":"https://github.com/cmsflash/efficient-attention"},{"title":"tea1528/Non-Local-NN-Pytorch","url":"https://github.com/tea1528/Non-Local-NN-Pytorch"},{"title":"vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks","url":"https://github.com/vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks"},{"title":"franknb/Self-attention-DCGAN","url":"https://github.com/franknb/Self-attention-DCGAN"},{"title":"mirthai/csa-net","url":"https://github.com/mirthai/csa-net"},{"title":"tinymilky/RSANet","url":"https://github.com/tinymilky/RSANet"},{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"},{"title":"seominseok0429/inception-I3D-NON-LOCAL","url":"https://github.com/seominseok0429/inception-I3D-NON-LOCAL"},{"title":"jpviguerasguillen/feedback-non-local-attention-fnla","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention-fnla"},{"title":"JiaPeng1234/MRI-Segmentation-Transformer","url":"https://github.com/JiaPeng1234/MRI-Segmentation-Transformer"},{"title":"jpviguerasguillen/feedback-non-local-attention_fNLA","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention_fNLA"},{"title":"huyz1117/Non_Local_Net_TensorFlow","url":"https://github.com/huyz1117/Non_Local_Net_TensorFlow"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/Non_local"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/Non_local"},{"title":"WavesUR/embedded_TSM","url":"https://github.com/WavesUR/embedded_TSM"},{"title":"sunutf/TSM","url":"https://github.com/sunutf/TSM"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/I3D"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/Non_local"},{"title":"changliu816/CV-paper-review","url":"https://github.com/changliu816/CV-paper-review"},{"title":"jiajunhua/facebookresearch-Detectron","url":"https://github.com/jiajunhua/facebookresearch-Detectron"},{"title":"owena11/papers","url":"https://github.com/owena11/papers"},{"title":"LRacoci/permutation-graphml","url":"https://github.com/LRacoci/permutation-graphml"},{"title":"jordiae/DeepLearning-MAI","url":"https://github.com/jordiae/DeepLearning-MAI"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/Non_local"},{"title":"Aprilkaka/nonlocal_mindspore","url":"https://github.com/Aprilkaka/nonlocal_mindspore"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/Non_local"},{"title":"rijuldhir/TSM","url":"https://github.com/rijuldhir/TSM"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85703,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask Scoring R-CNN (ResNet-50 FPN)","metrics":{"mask AP":"36.0"},"paper_url":"http://arxiv.org/abs/1903.00241v1","paper_title":"Mask Scoring R-CNN","paper_date":"2019-03-01","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"zjhuang22/maskscoring_rcnn","url":"https://github.com/zjhuang22/maskscoring_rcnn"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MTCNN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85704,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"57.1","AP75":"38.0","APL":"48.7","APM":"39","APS":"19.1","mask AP":"35.8"},"paper_url":"https://arxiv.org/abs/2004.13665v2","paper_title":"A novel Region of Interest Extraction Layer for Instance Segmentation","paper_date":"2020-04-28","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/tree/master/configs/groie"},{"title":"IMPLabUniPr/mmdetection-groie","url":"https://github.com/IMPLabUniPr/mmdetection-groie"},{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"},{"title":"Gugan0905/steel-defect-detection","url":"https://github.com/Gugan0905/steel-defect-detection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85705,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Faster R-CNN (Res2Net-50)","metrics":{"AP50":"57.6","APL":"53.7","APM":"37.9","APS":"15.7","mask AP":"35.6"},"paper_url":"https://arxiv.org/abs/1904.01169v3","paper_title":"Res2Net: A New Multi-scale Backbone Architecture","paper_date":"2019-04-02","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"PaddlePaddle/PaddleClas","url":"https://github.com/PaddlePaddle/PaddleClas"},{"title":"open-mmlab/mmclassification","url":"https://github.com/open-mmlab/mmclassification"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"Res2Net/Res2Net-PretrainedModels","url":"https://github.com/Res2Net/Res2Net-PretrainedModels"},{"title":"gasvn/Res2Net","url":"https://github.com/gasvn/Res2Net"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/res2net"},{"title":"mindspore-ecosystem/mindcv","url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/res2net.py"},{"title":"Res2Net/Res2Net-maskrcnn","url":"https://github.com/Res2Net/Res2Net-maskrcnn"},{"title":"Res2Net/Res2Net-PoolNet","url":"https://github.com/Res2Net/Res2Net-PoolNet"},{"title":"Res2Net/mmdetection","url":"https://github.com/Res2Net/mmdetection"},{"title":"Res2Net/Res2Net-Pose-Estimation","url":"https://github.com/Res2Net/Res2Net-Pose-Estimation"},{"title":"zhuhongwei1999/bsa-net","url":"https://github.com/zhuhongwei1999/bsa-net"},{"title":"fupiao1998/res2net-keras","url":"https://github.com/fupiao1998/res2net-keras"},{"title":"ChrisMats/Res2Net","url":"https://github.com/ChrisMats/Res2Net"},{"title":"yfreedomliTHU/Res2Net","url":"https://github.com/yfreedomliTHU/Res2Net"},{"title":"IMvision12/keras-vision-models","url":"https://github.com/IMvision12/keras-vision-models"},{"title":"MS-Mind/MS-Code-02","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/res2net"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/ResNeXt"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/res2net_deeplabv3"},{"title":"tuanzhangCS/res2net-on-mxnet","url":"https://github.com/tuanzhangCS/res2net-on-mxnet"},{"title":"kingcong/res2net","url":"https://github.com/kingcong/res2net"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net_deeplabv3"},{"title":"2023-MindSpore-4/Code14","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/res2net"},{"title":"MindSpore-scientific/code-14","url":"https://github.com/MindSpore-scientific/code-14/tree/main/res_mlp_ms"},{"title":"Mind23-2/MindCode-114","url":"https://github.com/Mind23-2/MindCode-114"},{"title":"yangyucheng000/res2net","url":"https://github.com/yangyucheng000/res2net/blob/main/res2net.py"},{"title":"2023-MindSpore-1/ms-code-216","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/res2net"},{"title":"MindSpore-paper-code-3/code5","url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/ResNeXt"},{"title":"MindSpore-paper-code-3/code5","url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/res2net_deeplabv3"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/res2net"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85706,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ResNet-50, +1 NL)","metrics":{"mask AP":"35.5"},"paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","paper_date":"2017-11-21","code_links":[{"title":"facebookresearch/detectron","url":"https://github.com/facebookresearch/detectron"},{"title":"facebookresearch/SlowFast","url":"https://github.com/facebookresearch/SlowFast"},{"title":"open-mmlab/mmaction2","url":"https://github.com/open-mmlab/mmaction2"},{"title":"MIT-HAN-LAB/temporal-shift-module","url":"https://github.com/MIT-HAN-LAB/temporal-shift-module"},{"title":"facebookresearch/video-nonlocal-net","url":"https://github.com/facebookresearch/video-nonlocal-net"},{"title":"cmsflash/efficient-attention","url":"https://github.com/cmsflash/efficient-attention"},{"title":"tea1528/Non-Local-NN-Pytorch","url":"https://github.com/tea1528/Non-Local-NN-Pytorch"},{"title":"vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks","url":"https://github.com/vanoracai/Exploiting-Spatial-temporal-Relationships-for-3D-Pose-Estimation-via-Graph-Convolutional-Networks"},{"title":"franknb/Self-attention-DCGAN","url":"https://github.com/franknb/Self-attention-DCGAN"},{"title":"mirthai/csa-net","url":"https://github.com/mirthai/csa-net"},{"title":"tinymilky/RSANet","url":"https://github.com/tinymilky/RSANet"},{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"},{"title":"seominseok0429/inception-I3D-NON-LOCAL","url":"https://github.com/seominseok0429/inception-I3D-NON-LOCAL"},{"title":"jpviguerasguillen/feedback-non-local-attention-fnla","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention-fnla"},{"title":"JiaPeng1234/MRI-Segmentation-Transformer","url":"https://github.com/JiaPeng1234/MRI-Segmentation-Transformer"},{"title":"jpviguerasguillen/feedback-non-local-attention_fNLA","url":"https://github.com/jpviguerasguillen/feedback-non-local-attention_fNLA"},{"title":"huyz1117/Non_Local_Net_TensorFlow","url":"https://github.com/huyz1117/Non_Local_Net_TensorFlow"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/Non_local"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/Non_local"},{"title":"WavesUR/embedded_TSM","url":"https://github.com/WavesUR/embedded_TSM"},{"title":"sunutf/TSM","url":"https://github.com/sunutf/TSM"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/I3D"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/Non_local"},{"title":"changliu816/CV-paper-review","url":"https://github.com/changliu816/CV-paper-review"},{"title":"jiajunhua/facebookresearch-Detectron","url":"https://github.com/jiajunhua/facebookresearch-Detectron"},{"title":"owena11/papers","url":"https://github.com/owena11/papers"},{"title":"LRacoci/permutation-graphml","url":"https://github.com/LRacoci/permutation-graphml"},{"title":"jordiae/DeepLearning-MAI","url":"https://github.com/jordiae/DeepLearning-MAI"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/Non_local"},{"title":"Aprilkaka/nonlocal_mindspore","url":"https://github.com/Aprilkaka/nonlocal_mindspore"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/Non_local"},{"title":"rijuldhir/TSM","url":"https://github.com/rijuldhir/TSM"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85707,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"Mask R-CNN (ResNet-50, ACNet)","metrics":{"mask AP":"35.2"},"paper_url":"http://arxiv.org/abs/1904.03579v1","paper_title":"Adaptively Connected Neural Networks","paper_date":"2019-04-07","code_links":[{"title":"wanggrun/Adaptively-Connected-Neural-Networks","url":"https://github.com/wanggrun/Adaptively-Connected-Neural-Networks"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85708,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"YOLACT-550 (ResNet-50)","metrics":{"mask AP":"29.9"},"paper_url":"https://arxiv.org/abs/1904.02689v2","paper_title":"YOLACT: Real-time Instance Segmentation","paper_date":"2019-04-04","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"dbolya/yolact","url":"https://github.com/dbolya/yolact"},{"title":"youngwanLEE/CenterMask","url":"https://github.com/youngwanLEE/CenterMask"},{"title":"feiyuhuahuo/Yolact_minimal","url":"https://github.com/feiyuhuahuo/Yolact_minimal"},{"title":"leohsuofnthu/Tensorflow-YOLACT","url":"https://github.com/leohsuofnthu/Tensorflow-YOLACT"},{"title":"DataXujing/yolact_pytorch","url":"https://github.com/DataXujing/yolact_pytorch"},{"title":"anshkumar/yolact","url":"https://github.com/anshkumar/yolact"},{"title":"Ma-Dan/Yolact-CoreML","url":"https://github.com/Ma-Dan/Yolact-CoreML"},{"title":"KevinJia1212/yolact_cityscapes_550","url":"https://github.com/KevinJia1212/yolact_cityscapes_550"},{"title":"Jittor/InstanceSegmentation-jittor","url":"https://github.com/Jittor/InstanceSegmentation-jittor"},{"title":"kaylode/Clothes-Segmentation","url":"https://github.com/kaylode/Clothes-Segmentation"},{"title":"lasithaya/yolact","url":"https://github.com/lasithaya/yolact"},{"title":"adityarc19/yolact-plus","url":"https://github.com/adityarc19/yolact-plus"},{"title":"SpaceView/Yolact_EfficientNet","url":"https://github.com/SpaceView/Yolact_EfficientNet"},{"title":"adityarc19/traffic-vehicles-instance-segmentation","url":"https://github.com/adityarc19/traffic-vehicles-instance-segmentation"},{"title":"kaylode/Trash-Segmentation","url":"https://github.com/kaylode/Trash-Segmentation"},{"title":"banayoyo/yoolact","url":"https://github.com/banayoyo/yoolact"},{"title":"SharifElfouly/easy-model-zoo","url":"https://github.com/SharifElfouly/easy-model-zoo"},{"title":"hakillha/yolact_yx","url":"https://github.com/hakillha/yolact_yx"},{"title":"IntelligenceDatum/ICCV2019_Model_Compression","url":"https://github.com/IntelligenceDatum/ICCV2019_Model_Compression"},{"title":"Abhijeet8901/Instance-Segmentation-using-YOLACT","url":"https://github.com/Abhijeet8901/Instance-Segmentation-using-YOLACT"},{"title":"zzuxzt/yolact_cpu","url":"https://github.com/zzuxzt/yolact_cpu"},{"title":"DivaniMandi/myCustomDataset_yolact","url":"https://github.com/DivaniMandi/myCustomDataset_yolact"},{"title":"jiajunhua/dbolya-yolact","url":"https://github.com/jiajunhua/dbolya-yolact"},{"title":"zhaozhongch/yolact_ros","url":"https://github.com/zhaozhongch/yolact_ros"},{"title":"Hoang-it/orhcid_classification","url":"https://github.com/Hoang-it/orhcid_classification"},{"title":"YeshengSu/Yolact","url":"https://github.com/YeshengSu/Yolact"},{"title":"NSCL/yolact_instance","url":"https://github.com/NSCL/yolact_instance"},{"title":"hz-ants/yolact","url":"https://github.com/hz-ants/yolact"},{"title":"leenajyotishi/objectdetectionstuff","url":"https://github.com/leenajyotishi/objectdetectionstuff"},{"title":"eddy4112/Yolact","url":"https://github.com/eddy4112/Yolact"},{"title":"songjmcn/yolact","url":"https://github.com/songjmcn/yolact"},{"title":"skritik098/new_yolact_2","url":"https://github.com/skritik098/new_yolact_2"},{"title":"KHKHG/yolact","url":"https://github.com/KHKHG/yolact"},{"title":"skritik098/new_yolact","url":"https://github.com/skritik098/new_yolact"},{"title":"divyachandana/yolact","url":"https://github.com/divyachandana/yolact"},{"title":"hyunahOh/instance_segmentation","url":"https://github.com/hyunahOh/instance_segmentation"},{"title":"hampen2929/yolact","url":"https://github.com/hampen2929/yolact"},{"title":"lucasfporto/yolactTest","url":"https://github.com/lucasfporto/yolactTest"},{"title":"bihanli/yolactBH","url":"https://github.com/bihanli/yolactBH"},{"title":"artneer/yolact","url":"https://github.com/artneer/yolact"},{"title":"zhawhjw/yolact-interpret","url":"https://github.com/zhawhjw/yolact-interpret"},{"title":"zhhchen4njit/yolact","url":"https://github.com/zhhchen4njit/yolact"},{"title":"BigThreeMI/Utils","url":"https://github.com/BigThreeMI/Utils"},{"title":"hololee/YOLACT","url":"https://github.com/hololee/YOLACT"},{"title":"jay-z20/yolact-paddle","url":"https://github.com/jay-z20/yolact-paddle"},{"title":"stuartchen1949/yolact-paddle","url":"https://github.com/stuartchen1949/yolact-paddle"},{"title":"Yahya1547/FaceMask","url":"https://github.com/Yahya1547/FaceMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85709,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO minival","model_name":"InternImage-B","metrics":{"GFLOPs":"501","Params (M)":"115"},"paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","paper_date":"2022-11-10","code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APL\", \"APM\", \"APS\", \"GFLOPs\", \"Params (M)\", \"box AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}