{"task":"Instance Segmentation","dataset":"COCO test-dev","metric_names":["mask AP","AP50","AP75","APS","APM","APL"],"rows":[{"id":85756,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Co-DETR","metrics":{"AP50":"80.2","AP75":"63.4","APL":"72.0","APM":"60.1","APS":"41.6","mask AP":"57.1"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85757,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CBNetV2 (EVA02, single-scale)","metrics":{"AP50":"80.3","AP75":"62.1","APL":"70.9","APM":"59.3","APS":"39.7","mask AP":"56.1"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85758,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"EVA","metrics":{"AP50":"80.0","APL":"72.4","APM":"58.0","APS":"36.3","mask AP":"55.5"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85759,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"FD-SwinV2-G","metrics":{"mask AP":"55.4"},"paper_url":"https://arxiv.org/abs/2205.14141v3","paper_title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","paper_date":"2022-05-27","code_links":[{"title":"SwinTransformer/Feature-Distillation","url":"https://github.com/SwinTransformer/Feature-Distillation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85760,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask Frozen-DETR","metrics":{"AP50":"79.3","AP75":"61.4","APL":"70.4","APM":"58.4","APS":"37.8","mask AP":"55.3"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85761,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"BEiT-3","metrics":{"mask AP":"54.8"},"paper_url":"https://arxiv.org/abs/2208.10442v2","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","paper_date":"2022-08-22","code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/beit"},{"title":"lyan62/data-curation","url":"https://github.com/lyan62/data-curation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85762,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MasK DINO (SwinL, multi-scale)","metrics":{"mask AP":"54.7"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85763,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)","metrics":{"mask AP":"54.5"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85764,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"GLEE-Pro","metrics":{"mask AP":"54.5"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85765,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SwinV2-G (HTC++)","metrics":{"mask AP":"54.4"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85766,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"GLEE-Plus","metrics":{"mask AP":"53.3"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85767,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Soft Teacher + Swin-L (HTC++, multi-scale)","metrics":{"mask AP":"53.0"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85768,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ViT-Adapter-L (HTC++, BEiTv2 pretrain, multi-scale)","metrics":{"mask AP":"53.0"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85769,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask DINO (SwinL, single -scale)","metrics":{"mask AP":"52.8"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85770,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ViT-Adapter-L (HTC++, BEiT 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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85771,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"mask AP":"52.3"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85772,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"UNINEXT-H","metrics":{"AP50":"76.2","AP75":"56.7","APL":"67.5","APM":"55.9","APS":"33.3","mask AP":"51.8"},"paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","paper_date":"2023-03-12","code_links":[{"title":"MasterBin-IIAU/UNINEXT","url":"https://github.com/MasterBin-IIAU/UNINEXT"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85773,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CBNetV2 (Dual-Swin-L HTC, single-scale)","metrics":{"mask AP":"51.6"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85774,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Focal-L (HTC++, multi-scale)","metrics":{"AP50":"75.4","AP75":"56.5","APL":"64.2","APS":"35.6","mask AP":"51.3"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85775,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Swin-L (HTC++, multi scale)","metrics":{"mask AP":"51.1"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85776,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask2Former (Swin-L, single scale)","metrics":{"AP50":"74.9","AP75":"54.9","APL":"71.2","APM":"53.8","APS":"29.1","mask AP":"50.5"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85777,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Swin-L (HTC++, single scale)","metrics":{"mask AP":"50.2"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85778,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ISTR-SMT (Swin-L, single scale)","metrics":{"mask AP":"49.7"},"paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","paper_date":"2021-05-03","code_links":[{"title":"hujiecpp/ISTR","url":"https://github.com/hujiecpp/ISTR"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85779,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"QueryInst (single scale)","metrics":{"AP50":"74.2","AP75":"53.8","APL":"63.2","APM":"51.8","APS":"31.5","mask AP":"49.1"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85780,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)","metrics":{"mask AP":"49.1"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85781,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"dBOT ViT-L (CLIP)","metrics":{"mask AP":"48.8"},"paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","paper_date":"2022-09-08","code_links":[{"title":"liuxingbin/dbot","url":"https://github.com/liuxingbin/dbot"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85782,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-XL (Cascade Mask R-CNN)","metrics":{"mask AP":"48.8"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85783,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DetectoRS (ResNeXt-101-64x4d, multi-scale)","metrics":{"AP50":"72.0","AP75":"53.3","APL":"61.5","APM":"50.9","APS":"31.6","mask AP":"48.5"},"paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","paper_date":"2020-06-03","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"joe-siyuan-qiao/DetectoRS","url":"https://github.com/joe-siyuan-qiao/DetectoRS"},{"title":"FenHua/Robust_Logo_Detection","url":"https://github.com/FenHua/Robust_Logo_Detection"},{"title":"Vishal-V/tf-models","url":"https://github.com/Vishal-V/tf-models"},{"title":"TeamA2020/Practice","url":"https://github.com/TeamA2020/Practice"},{"title":"novav/DetectoRS_Colab","url":"https://github.com/novav/DetectoRS_Colab"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85784,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"dBOT ViT-L","metrics":{"mask AP":"48.3"},"paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","paper_date":"2022-09-08","code_links":[{"title":"liuxingbin/dbot","url":"https://github.com/liuxingbin/dbot"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85785,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DiffusionInst-SwinL","metrics":{"mask AP":"48.3"},"paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","paper_date":"2022-12-06","code_links":[{"title":"chenhaoxing/DiffusionInst","url":"https://github.com/chenhaoxing/DiffusionInst"},{"title":"alipay/diffusion-model-for-instance-segmentation","url":"https://github.com/alipay/diffusion-model-for-instance-segmentation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85786,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"GLEE-Lite","metrics":{"mask AP":"48.3"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85787,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DiffusionInst-SwinB","metrics":{"mask AP":"47.6"},"paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","paper_date":"2022-12-06","code_links":[{"title":"chenhaoxing/DiffusionInst","url":"https://github.com/chenhaoxing/DiffusionInst"},{"title":"alipay/diffusion-model-for-instance-segmentation","url":"https://github.com/alipay/diffusion-model-for-instance-segmentation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85788,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DetectoRS (ResNeXt-101-32x4d, multi-scale)","metrics":{"AP50":"71.1","AP75":"51.6","APL":"59.6","APM":"49.5","APS":"30.3","mask AP":"47.1"},"paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","paper_date":"2020-06-03","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"joe-siyuan-qiao/DetectoRS","url":"https://github.com/joe-siyuan-qiao/DetectoRS"},{"title":"FenHua/Robust_Logo_Detection","url":"https://github.com/FenHua/Robust_Logo_Detection"},{"title":"Vishal-V/tf-models","url":"https://github.com/Vishal-V/tf-models"},{"title":"TeamA2020/Practice","url":"https://github.com/TeamA2020/Practice"},{"title":"novav/DetectoRS_Colab","url":"https://github.com/novav/DetectoRS_Colab"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85789,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Cascade Eff-B7 NAS-FPN (1280)","metrics":{"mask AP":"46.9"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85790,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOLQ (Swin-L, single scale)","metrics":{"mask AP":"46.7"},"paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","paper_date":"2021-06-04","code_links":[{"title":"megvii-research/SOLQ","url":"https://github.com/megvii-research/SOLQ"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85791,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"dBOT ViT-B","metrics":{"mask AP":"46.3"},"paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","paper_date":"2022-09-08","code_links":[{"title":"liuxingbin/dbot","url":"https://github.com/liuxingbin/dbot"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85792,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"dBOT ViT-B (CLIP)","metrics":{"mask AP":"46.2"},"paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","paper_date":"2022-09-08","code_links":[{"title":"liuxingbin/dbot","url":"https://github.com/liuxingbin/dbot"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85793,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask R-CNN (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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85794,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-L (Cascade Mask R-CNN)","metrics":{"mask AP":"46.1"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85795,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-B (Cascade Mask R-CNN)","metrics":{"mask AP":"46"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85796,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Swin-B + Cascade Mask R-CNN (tri-layer modelling)","metrics":{"mask AP":"45.9"},"paper_url":"https://arxiv.org/abs/2210.10046v1","paper_title":"A Tri-Layer Plugin to Improve Occluded Detection","paper_date":"2022-10-18","code_links":[{"title":"Championchess/Tri-Layer_Plugin_Occluded_Detection","url":"https://github.com/Championchess/Tri-Layer_Plugin_Occluded_Detection"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85797,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"GCNet (ResNeXt-101 + DCN + cascade + GC r4)","metrics":{"AP50":"68.9","AP75":"49.6","mask AP":"45.4"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85798,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-S (Cascade Mask R-CNN)","metrics":{"mask AP":"45.1"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85799,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"gSwin-S","metrics":{"mask AP":"45.03"},"paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","paper_date":"2022-08-24","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85800,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"iBOT (ViT-B/16)","metrics":{"mask AP":"44.2"},"paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","paper_date":"2021-11-15","code_links":[{"title":"bytedance/ibot","url":"https://github.com/bytedance/ibot"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85801,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"gSwin-T","metrics":{"mask AP":"44.16"},"paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","paper_date":"2022-08-24","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85802,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-L (Mask R-CNN 1x)","metrics":{"mask AP":"44.1"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85803,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"A2MIM (ViT-B)","metrics":{"mask AP":"43.5"},"paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","paper_date":"2022-05-27","code_links":[{"title":"open-mmlab/mmpretrain","url":"https://github.com/open-mmlab/mmpretrain"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"Westlake-AI/A2MIM","url":"https://github.com/Westlake-AI/A2MIM"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85804,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Cascade Mask R-CNN (ResNeXt152, CBNet)","metrics":{"mask AP":"43.3"},"paper_url":"https://arxiv.org/abs/1909.03625v1","paper_title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","paper_date":"2019-09-09","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"PKUbahuangliuhe/CBNet","url":"https://github.com/PKUbahuangliuhe/CBNet"},{"title":"QiaoranC/tf_ResNeSt_RegNet_model","url":"https://github.com/QiaoranC/tf_ResNeSt_RegNet_model"},{"title":"panjianning/cbnet","url":"https://github.com/panjianning/cbnet"},{"title":"Adrian398/CB-Net-EDD","url":"https://github.com/Adrian398/CB-Net-EDD"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85805,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-B (Mask R-CNN 1x)","metrics":{"mask AP":"43.2"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85806,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ResNeSt101","metrics":{"mask AP":"43%"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85807,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"gSwin-VT","metrics":{"mask AP":"42.87"},"paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","paper_date":"2022-08-24","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85808,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"iBOT (ViT-S/16)","metrics":{"mask AP":"42.6"},"paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","paper_date":"2021-11-15","code_links":[{"title":"bytedance/ibot","url":"https://github.com/bytedance/ibot"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85809,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask Transfiner(ResNet101-FPN)","metrics":{"mask AP":"42.2"},"paper_url":"https://arxiv.org/abs/2111.13673v1","paper_title":"Mask Transfiner for High-Quality Instance Segmentation","paper_date":"2021-11-26","code_links":[{"title":"SysCV/transfiner","url":"https://github.com/SysCV/transfiner"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85810,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-S (Mask R-CNN 1x)","metrics":{"mask AP":"42.2"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85811,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"PANet","metrics":{"mask AP":"42.0"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85812,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CenterMask + VoVNet99","metrics":{"APL":"54.3","APM":"44.4","APS":"24.4","mask AP":"41.8"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85813,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOLOv2(Res-DCN-101-FPN)","metrics":{"AP50":"63.2","AP75":"45.1","APL":"61.6","APM":"45.0","APS":"18.0","mask AP":"41.7"},"paper_url":"https://arxiv.org/abs/2003.10152v3","paper_title":"SOLOv2: Dynamic and Fast Instance Segmentation","paper_date":"2020-03-23","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"WXinlong/SOLO","url":"https://github.com/WXinlong/SOLO"},{"title":"zymk9/Yet-Another-Anime-Segmenter","url":"https://github.com/zymk9/Yet-Another-Anime-Segmenter"},{"title":"OpenFirework/pytorch_solov2","url":"https://github.com/OpenFirework/pytorch_solov2"},{"title":"fastestimator/fastestimator","url":"https://github.com/fastestimator/fastestimator/blob/master/apphub/instance_segmentation/solov2/solov2_tf.py"},{"title":"lifuguan/SOLOv2-mmdet","url":"https://github.com/lifuguan/SOLOv2-mmdet"},{"title":"Fei-dong/SOLO_SORT","url":"https://github.com/Fei-dong/SOLO_SORT"},{"title":"mvpzhangqiu/SOLOV2","url":"https://github.com/mvpzhangqiu/SOLOV2"},{"title":"hukefei/SOLO-master","url":"https://github.com/hukefei/SOLO-master"},{"title":"universea/SOLOv2","url":"https://github.com/universea/SOLOv2"},{"title":"hades12580/solov2_mmdet","url":"https://github.com/hades12580/solov2_mmdet"},{"title":"MY-Swich/solo-len","url":"https://github.com/MY-Swich/solo-len"},{"title":"trhieu310/customDataset","url":"https://github.com/trhieu310/customDataset"},{"title":"MY-Swich/SOLO","url":"https://github.com/MY-Swich/SOLO"},{"title":"MY-Swich/SOLO_my","url":"https://github.com/MY-Swich/SOLO_my"},{"title":"divyachandana/solo-semantic-segmentation","url":"https://github.com/divyachandana/solo-semantic-segmentation"},{"title":"XXXVincent/SOLO","url":"https://github.com/XXXVincent/SOLO"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85814,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"BCNet(ResNeXt-101  + FPN+ FCOS)","metrics":{"mask AP":"41.7"},"paper_url":"https://arxiv.org/abs/2103.12340v1","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","paper_date":"2021-03-23","code_links":[{"title":"lkeab/BCNet","url":"https://github.com/lkeab/BCNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85815,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"GCNet (ResNeXt-101 + DCN + cascade + GC r16)","metrics":{"mask AP":"41.5%"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85816,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DiffusionInst-ResNet101","metrics":{"mask AP":"41.5"},"paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","paper_date":"2022-12-06","code_links":[{"title":"chenhaoxing/DiffusionInst","url":"https://github.com/chenhaoxing/DiffusionInst"},{"title":"alipay/diffusion-model-for-instance-segmentation","url":"https://github.com/alipay/diffusion-model-for-instance-segmentation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85817,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"BlendMask (ResNet-101 + DCN interval=3)","metrics":{"AP50":"63.1","AP75":"44.6","APL":"54.5","APM":"44.1","APS":"22.7","mask AP":"41.3"},"paper_url":"https://arxiv.org/abs/2001.00309v3","paper_title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","paper_date":"2020-01-02","code_links":[{"title":"aim-uofa/AdelaiDet","url":"https://github.com/aim-uofa/AdelaiDet"},{"title":"aim-uofa/adet","url":"https://github.com/aim-uofa/adet"},{"title":"nerminsamet/houghnet","url":"https://github.com/nerminsamet/houghnet"},{"title":"TengFeiHan0/Instance-Wise-Depth","url":"https://github.com/TengFeiHan0/Instance-Wise-Depth"},{"title":"blueardour/AdelaiDet","url":"https://github.com/blueardour/AdelaiDet"},{"title":"Pxtri2156/AdelaiDet_v2","url":"https://github.com/Pxtri2156/AdelaiDet_v2"},{"title":"quangvy2703/ABCNet-ESRGAN-SRTEXT","url":"https://github.com/quangvy2703/ABCNet-ESRGAN-SRTEXT"},{"title":"zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection","url":"https://github.com/zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection"},{"title":"zhubinQAQ/Ins","url":"https://github.com/zhubinQAQ/Ins"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85818,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"HTC + ResNeXt-101-FPN + DCN","metrics":{"mask AP":"41.2"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85819,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"HTC + ResNeXt-101-FPN","metrics":{"mask AP":"41.2%"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85820,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOLQ (ResNet101, single scale)","metrics":{"mask AP":"40.9"},"paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","paper_date":"2021-06-04","code_links":[{"title":"megvii-research/SOLQ","url":"https://github.com/megvii-research/SOLQ"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85821,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"VoVNetV1-57","metrics":{"mask AP":"40.8%"},"paper_url":"http://arxiv.org/abs/1904.09730v1","paper_title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","paper_date":"2019-04-22","code_links":[{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"youngwanLEE/vovnet-detectron2","url":"https://github.com/youngwanLEE/vovnet-detectron2"},{"title":"stigma0617/VoVNet.pytorch","url":"https://github.com/stigma0617/VoVNet.pytorch"},{"title":"vov-net/VoVNet-FCOS","url":"https://github.com/vov-net/VoVNet-FCOS"},{"title":"youngwanLEE/VoVNet-RefineDet","url":"https://github.com/youngwanLEE/VoVNet-RefineDet"},{"title":"vov-net/VoVNet-Detectron","url":"https://github.com/vov-net/VoVNet-Detectron"},{"title":"stigma0617/maskrcnn-benchmark-vovnet","url":"https://github.com/stigma0617/maskrcnn-benchmark-vovnet"},{"title":"stigma0617/VoVNet-DeepLabV3","url":"https://github.com/stigma0617/VoVNet-DeepLabV3"},{"title":"2anchao/VovJpu","url":"https://github.com/2anchao/VovJpu"},{"title":"suvasis/birdnet2cs231n","url":"https://github.com/suvasis/birdnet2cs231n"},{"title":"neilctwu/FCOS-pytorch_Simplified","url":"https://github.com/neilctwu/FCOS-pytorch_Simplified"},{"title":"Dandelight/VoVNet-PaddlePaddle","url":"https://github.com/Dandelight/VoVNet-PaddlePaddle"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85822,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"K-Net-N256 (ResNet-101)","metrics":{"AP50":"63.3","APL":"59","APM":"43.3","APS":"18.8","mask AP":"40.6%"},"paper_url":"https://arxiv.org/abs/2106.14855v2","paper_title":"K-Net: Towards Unified Image Segmentation","paper_date":"2021-06-28","code_links":[{"title":"zwwwayne/k-net","url":"https://github.com/zwwwayne/k-net"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85823,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CenterMask + VoVNetV2-99 (single-scale)","metrics":{"AP50":"62.3","AP75":"44.1","APL":"57.0","APM":"42.8","APS":"20.1","mask AP":"40.6"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85824,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOLO(Res-DCN-101-FPN)","metrics":{"AP50":"62.7","AP75":"43.3","APL":"58.9","APM":"43.3","APS":"17.6","mask AP":"40.4"},"paper_url":"https://arxiv.org/abs/1912.04488v3","paper_title":"SOLO: Segmenting Objects by Locations","paper_date":"2019-12-10","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"aim-uofa/AdelaiDet","url":"https://github.com/aim-uofa/AdelaiDet"},{"title":"aim-uofa/adet","url":"https://github.com/aim-uofa/adet"},{"title":"WXinlong/SOLO","url":"https://github.com/WXinlong/SOLO"},{"title":"dqxiu/kassess","url":"https://github.com/dqxiu/kassess"},{"title":"TengFeiHan0/Instance-Wise-Depth","url":"https://github.com/TengFeiHan0/Instance-Wise-Depth"},{"title":"quanghona/SOLO_tf2","url":"https://github.com/quanghona/SOLO_tf2"},{"title":"blueardour/AdelaiDet","url":"https://github.com/blueardour/AdelaiDet"},{"title":"Pxtri2156/AdelaiDet_v2","url":"https://github.com/Pxtri2156/AdelaiDet_v2"},{"title":"quangvy2703/ABCNet-ESRGAN-SRTEXT","url":"https://github.com/quangvy2703/ABCNet-ESRGAN-SRTEXT"},{"title":"zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection","url":"https://github.com/zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection"},{"title":"Fei-dong/SOLO_SORT","url":"https://github.com/Fei-dong/SOLO_SORT"},{"title":"zhubinQAQ/Ins","url":"https://github.com/zhubinQAQ/Ins"},{"title":"mvpzhangqiu/SOLOV2","url":"https://github.com/mvpzhangqiu/SOLOV2"},{"title":"hukefei/SOLO-master","url":"https://github.com/hukefei/SOLO-master"},{"title":"MaiHon/Solo","url":"https://github.com/MaiHon/Solo"},{"title":"hades12580/solov2_mmdet","url":"https://github.com/hades12580/solov2_mmdet"},{"title":"MY-Swich/solo-len","url":"https://github.com/MY-Swich/solo-len"},{"title":"divyachandana/solo-semantic-segmentation","url":"https://github.com/divyachandana/solo-semantic-segmentation"},{"title":"XXXVincent/SOLO","url":"https://github.com/XXXVincent/SOLO"},{"title":"trhieu310/customDataset","url":"https://github.com/trhieu310/customDataset"},{"title":"MY-Swich/SOLO_my","url":"https://github.com/MY-Swich/SOLO_my"},{"title":"MY-Swich/SOLO","url":"https://github.com/MY-Swich/SOLO"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85825,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOLO (ResNet-DCN-101-FPN)","metrics":{"AP50":"62.7%","AP75":"43.3%","APL":"58.9%","APM":"43.3%","APS":"17.6%","mask AP":"40.4%"},"paper_url":"https://arxiv.org/abs/1912.04488v3","paper_title":"SOLO: Segmenting Objects by Locations","paper_date":"2019-12-10","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"aim-uofa/AdelaiDet","url":"https://github.com/aim-uofa/AdelaiDet"},{"title":"aim-uofa/adet","url":"https://github.com/aim-uofa/adet"},{"title":"WXinlong/SOLO","url":"https://github.com/WXinlong/SOLO"},{"title":"dqxiu/kassess","url":"https://github.com/dqxiu/kassess"},{"title":"TengFeiHan0/Instance-Wise-Depth","url":"https://github.com/TengFeiHan0/Instance-Wise-Depth"},{"title":"quanghona/SOLO_tf2","url":"https://github.com/quanghona/SOLO_tf2"},{"title":"blueardour/AdelaiDet","url":"https://github.com/blueardour/AdelaiDet"},{"title":"Pxtri2156/AdelaiDet_v2","url":"https://github.com/Pxtri2156/AdelaiDet_v2"},{"title":"quangvy2703/ABCNet-ESRGAN-SRTEXT","url":"https://github.com/quangvy2703/ABCNet-ESRGAN-SRTEXT"},{"title":"zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection","url":"https://github.com/zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection"},{"title":"Fei-dong/SOLO_SORT","url":"https://github.com/Fei-dong/SOLO_SORT"},{"title":"zhubinQAQ/Ins","url":"https://github.com/zhubinQAQ/Ins"},{"title":"mvpzhangqiu/SOLOV2","url":"https://github.com/mvpzhangqiu/SOLOV2"},{"title":"hukefei/SOLO-master","url":"https://github.com/hukefei/SOLO-master"},{"title":"MaiHon/Solo","url":"https://github.com/MaiHon/Solo"},{"title":"hades12580/solov2_mmdet","url":"https://github.com/hades12580/solov2_mmdet"},{"title":"MY-Swich/solo-len","url":"https://github.com/MY-Swich/solo-len"},{"title":"divyachandana/solo-semantic-segmentation","url":"https://github.com/divyachandana/solo-semantic-segmentation"},{"title":"XXXVincent/SOLO","url":"https://github.com/XXXVincent/SOLO"},{"title":"trhieu310/customDataset","url":"https://github.com/trhieu310/customDataset"},{"title":"MY-Swich/SOLO_my","url":"https://github.com/MY-Swich/SOLO_my"},{"title":"MY-Swich/SOLO","url":"https://github.com/MY-Swich/SOLO"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85826,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"D2Det (ResNet-101, single-scale test)","metrics":{"AP50":"61.5","AP75":"43.7","APL":"54.0","APM":"43.0","APS":"21.7","mask AP":"40.2"},"paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Cao_D2Det_Towards_High_Quality_Object_Detection_and_Instance_Segmentation_CVPR_2020_paper.html","paper_title":"D2Det: Towards High Quality Object Detection and Instance Segmentation","paper_date":"2020-06-01","code_links":[{"title":"JialeCao001/D2Det","url":"https://github.com/JialeCao001/D2Det"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85827,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"K-Net (ResNet-101)","metrics":{"AP50":"62.8","APL":"58.8","APM":"42.7","APS":"18.7","mask AP":"40.1%"},"paper_url":"https://arxiv.org/abs/2106.14855v2","paper_title":"K-Net: Towards Unified Image Segmentation","paper_date":"2021-06-28","code_links":[{"title":"zwwwayne/k-net","url":"https://github.com/zwwwayne/k-net"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85828,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ISTR (ResNet101-FPN-3x, single-scale)","metrics":{"APL":"52.3","APM":"41.9","APS":"22.8","mask AP":"39.9%"},"paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","paper_date":"2021-05-03","code_links":[{"title":"hujiecpp/ISTR","url":"https://github.com/hujiecpp/ISTR"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85829,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"BCNet(ResNet-101-FPN + Faster RCNN)","metrics":{"AP50":"61.5","AP75":"43.1","APL":"51.1","APM":"42.4","APS":"22.7","mask AP":"39.8"},"paper_url":"https://arxiv.org/abs/2103.12340v1","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","paper_date":"2021-03-23","code_links":[{"title":"lkeab/BCNet","url":"https://github.com/lkeab/BCNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85830,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"VoVNetV1-39","metrics":{"mask AP":"39.7%"},"paper_url":"http://arxiv.org/abs/1904.09730v1","paper_title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","paper_date":"2019-04-22","code_links":[{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"youngwanLEE/vovnet-detectron2","url":"https://github.com/youngwanLEE/vovnet-detectron2"},{"title":"stigma0617/VoVNet.pytorch","url":"https://github.com/stigma0617/VoVNet.pytorch"},{"title":"vov-net/VoVNet-FCOS","url":"https://github.com/vov-net/VoVNet-FCOS"},{"title":"youngwanLEE/VoVNet-RefineDet","url":"https://github.com/youngwanLEE/VoVNet-RefineDet"},{"title":"vov-net/VoVNet-Detectron","url":"https://github.com/vov-net/VoVNet-Detectron"},{"title":"stigma0617/maskrcnn-benchmark-vovnet","url":"https://github.com/stigma0617/maskrcnn-benchmark-vovnet"},{"title":"stigma0617/VoVNet-DeepLabV3","url":"https://github.com/stigma0617/VoVNet-DeepLabV3"},{"title":"2anchao/VovJpu","url":"https://github.com/2anchao/VovJpu"},{"title":"suvasis/birdnet2cs231n","url":"https://github.com/suvasis/birdnet2cs231n"},{"title":"neilctwu/FCOS-pytorch_Simplified","url":"https://github.com/neilctwu/FCOS-pytorch_Simplified"},{"title":"Dandelight/VoVNet-PaddlePaddle","url":"https://github.com/Dandelight/VoVNet-PaddlePaddle"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85831,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOLQ (ResNet50, single scale)","metrics":{"mask AP":"39.7"},"paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","paper_date":"2021-06-04","code_links":[{"title":"megvii-research/SOLQ","url":"https://github.com/megvii-research/SOLQ"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85832,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CenterMask + X101-32x8d (single-scale)","metrics":{"AP50":"61.2","AP75":"42.9","APS":"19.7","mask AP":"39.6"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85833,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"BCNet(ResNet-101-FPN + FCOS)","metrics":{"AP50":"61.2","AP75":"42.7","APL":"51.0","APM":"42.3","APS":"22.3","mask AP":"39.6"},"paper_url":"https://arxiv.org/abs/2103.12340v1","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","paper_date":"2021-03-23","code_links":[{"title":"lkeab/BCNet","url":"https://github.com/lkeab/BCNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85834,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MS R-CNN + ResNet-101 DCN + FPN ","metrics":{"mask AP":"39.6%"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85835,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Cascade R-CNN (ResNet-101-FPN, map-guided)","metrics":{"AP50":"61.4%","AP75":"42.9%","APL":"52.1%","APM":"42.5%","APS":"21.2%","mask AP":"39.5%"},"paper_url":"https://arxiv.org/abs/1908.07801v1","paper_title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","paper_date":"2019-08-21","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"GothicAi/InstaBoost","url":"https://github.com/GothicAi/InstaBoost"},{"title":"code-implementation1/Code4","url":"https://github.com/code-implementation1/Code4/tree/main/IndexNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85836,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CPMask","metrics":{"AP50":"60.8","AP75":"42.2","APL":"50.1","APM":"41.8","APS":"22.2","mask AP":"39.2"},"paper_url":"https://arxiv.org/abs/2007.12387v1","paper_title":"Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation","paper_date":"2020-07-24","code_links":[{"title":"fanq15/FewX","url":"https://github.com/fanq15/FewX"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85837,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-T (Mask R-CNN 1x)","metrics":{"mask AP":"39.1"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85838,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"PolarMask++ (ResNeXt-101-DCN)","metrics":{"AP50":"64.1","AP75":"40.0","APL":"52.0","APM":"40.2","APS":"22.2","mask AP":"38.7"},"paper_url":"https://arxiv.org/abs/2105.02184v1","paper_title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","paper_date":"2021-05-05","code_links":[{"title":"xieenze/PolarMask","url":"https://github.com/xieenze/PolarMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85839,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ISDA (ours)","metrics":{"AP50":"62","AP75":"41.1","APM":"41.2","APS":"17","mask AP":"38.7"},"paper_url":"https://arxiv.org/abs/2202.12251v1","paper_title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","paper_date":"2022-02-23","code_links":[{"title":"yingkaining/isda","url":"https://github.com/yingkaining/isda"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85840,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ISTR (ResNet50-FPN-3x, single-scale)","metrics":{"APL":"50.6","APM":"40.4","APS":"22.1","mask AP":"38.6%"},"paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","paper_date":"2021-05-03","code_links":[{"title":"hujiecpp/ISTR","url":"https://github.com/hujiecpp/ISTR"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85841,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CenterMask + ResNet-101-FPN","metrics":{"mask AP":"38.3"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85842,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SipMask (ResNet-101, single-scale test)","metrics":{"AP50":"60.2","AP75":"40.8","APL":"54.3","APM":"40.8","APS":"17.8","mask AP":"38.1"},"paper_url":"https://arxiv.org/abs/2007.14772v1","paper_title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","paper_date":"2020-07-29","code_links":[{"title":"JialeCao001/SipMask","url":"https://github.com/JialeCao001/SipMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85843,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MaskLab+ (ResNet-101, JFT)","metrics":{"mask AP":"38.1%"},"paper_url":"http://arxiv.org/abs/1712.04837v1","paper_title":"MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features","paper_date":"2017-12-13","code_links":[],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85844,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"EmbedMask (ResNet-101-FPN)","metrics":{"AP50":"59.1%","AP75":"40.3%","APL":"53%","APM":"40.4%","APS":"17.9%","mask AP":"37.7%"},"paper_url":"https://arxiv.org/abs/1912.01954v2","paper_title":"EmbedMask: Embedding Coupling for One-stage Instance Segmentation","paper_date":"2019-12-04","code_links":[{"title":"yinghdb/EmbedMask","url":"https://github.com/yinghdb/EmbedMask"},{"title":"TengFeiHan0/Instance-Wise-Depth","url":"https://github.com/TengFeiHan0/Instance-Wise-Depth"},{"title":"gakkiri/EmbedMask","url":"https://github.com/gakkiri/EmbedMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85845,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"EmbedMask(R-101-FPN)","metrics":{"AP50":"59.1","AP75":"40.3","APM":"40.4","APS":"17.9","mask AP":"37.7"},"paper_url":"https://arxiv.org/abs/1912.01954v2","paper_title":"EmbedMask: Embedding Coupling for One-stage Instance Segmentation","paper_date":"2019-12-04","code_links":[{"title":"yinghdb/EmbedMask","url":"https://github.com/yinghdb/EmbedMask"},{"title":"TengFeiHan0/Instance-Wise-Depth","url":"https://github.com/TengFeiHan0/Instance-Wise-Depth"},{"title":"gakkiri/EmbedMask","url":"https://github.com/gakkiri/EmbedMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85846,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-XT","metrics":{"mask AP":"37.6"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85847,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"TensorMask (ResNet-101-FPN)","metrics":{"mask AP":"37.3%"},"paper_url":"https://arxiv.org/abs/1903.12174v2","paper_title":"TensorMask: A Foundation for Dense Object Segmentation","paper_date":"2019-03-28","code_links":[{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2/tree/master/projects/TensorMask"},{"title":"suvasis/birdnet2cs231n","url":"https://github.com/suvasis/birdnet2cs231n"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85848,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask R-CNN (ResNeXt-101-FPN)","metrics":{"AP50":"60.0","AP75":"39.4","APL":"53.5","APM":"39.9","APS":"16.9","mask AP":"37.1"},"paper_url":"http://arxiv.org/abs/1703.06870v3","paper_title":"Mask R-CNN","paper_date":"2017-03-20","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/vision"},{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2"},{"title":"facebookresearch/detectron","url":"https://github.com/facebookresearch/detectron"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"facebookresearch/maskrcnn-benchmark","url":"https://github.com/facebookresearch/maskrcnn-benchmark"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN"},{"title":"charlesshang/fastmaskrcnn","url":"https://github.com/charlesshang/fastmaskrcnn"},{"title":"ZQPei/deep_sort_pytorch","url":"https://github.com/ZQPei/deep_sort_pytorch"},{"title":"tryolabs/luminoth","url":"https://github.com/tryolabs/luminoth"},{"title":"multimodallearning/pytorch-mask-rcnn","url":"https://github.com/multimodallearning/pytorch-mask-rcnn"},{"title":"TuSimple/mx-maskrcnn","url":"https://github.com/TuSimple/mx-maskrcnn"},{"title":"mic-dkfz/medicaldetectiontoolkit","url":"https://github.com/mic-dkfz/medicaldetectiontoolkit"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"ayoolaolafenwa/PixelLib","url":"https://github.com/ayoolaolafenwa/PixelLib"},{"title":"vimalabs/VIMA","url":"https://github.com/vimalabs/VIMA"},{"title":"ykasten/layered-neural-atlases","url":"https://github.com/ykasten/layered-neural-atlases"},{"title":"longcw/roialign.pytorch","url":"https://github.com/longcw/roialign.pytorch"},{"title":"jremillard/images-to-osm","url":"https://github.com/jremillard/images-to-osm"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"bethgelab/siamese-mask-rcnn","url":"https://github.com/bethgelab/siamese-mask-rcnn"},{"title":"Okery/PyTorch-Simple-MaskRCNN","url":"https://github.com/Okery/PyTorch-Simple-MaskRCNN"},{"title":"yubaoliu/rds-slam","url":"https://github.com/yubaoliu/rds-slam"},{"title":"crowdai/crowdai-mapping-challenge-mask-rcnn","url":"https://github.com/crowdai/crowdai-mapping-challenge-mask-rcnn"},{"title":"raymon-tian/hourglass-facekeypoints-detection","url":"https://github.com/raymon-tian/hourglass-facekeypoints-detection"},{"title":"mstfakts/building-detection-maskrcnn","url":"https://github.com/mstfakts/building-detection-maskrcnn"},{"title":"jasjeetIM/Mask-RCNN","url":"https://github.com/jasjeetIM/Mask-RCNN"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/maskrcnn"},{"title":"SUYEgit/Surgery-Robot-Detection-Segmentation","url":"https://github.com/SUYEgit/Surgery-Robot-Detection-Segmentation"},{"title":"KMnP/fashionpedia-api","url":"https://github.com/KMnP/fashionpedia-api"},{"title":"mirzaevinom/data_science_bowl_2018","url":"https://github.com/mirzaevinom/data_science_bowl_2018"},{"title":"DeNA/Chainer_Mask_R-CNN","url":"https://github.com/DeNA/Chainer_Mask_R-CNN"},{"title":"jianing-sun/Mask-YOLO","url":"https://github.com/jianing-sun/Mask-YOLO"},{"title":"RituYadav92/Radar-RGB-Attentive-Multimodal-Object-Detection","url":"https://github.com/RituYadav92/Radar-RGB-Attentive-Multimodal-Object-Detection"},{"title":"louisyuzhe/car-damage-detector","url":"https://github.com/louisyuzhe/car-damage-detector"},{"title":"AKASH2907/bird-species-classification","url":"https://github.com/AKASH2907/bird-species-classification"},{"title":"AKASH2907/bird_species_classification","url":"https://github.com/AKASH2907/bird_species_classification"},{"title":"NVlabs/industreallib","url":"https://github.com/NVlabs/industreallib"},{"title":"Lopezurrutia/DSB_2018","url":"https://github.com/Lopezurrutia/DSB_2018"},{"title":"lichengunc/mask-faster-rcnn","url":"https://github.com/lichengunc/mask-faster-rcnn"},{"title":"Burf/tfdetection","url":"https://github.com/Burf/tfdetection"},{"title":"EmGarr/kerod","url":"https://github.com/EmGarr/kerod"},{"title":"itsasimiqbal/SeBRe","url":"https://github.com/itsasimiqbal/SeBRe"},{"title":"BupyeongHealer/Mask_RCNN_tf_2.x","url":"https://github.com/BupyeongHealer/Mask_RCNN_tf_2.x"},{"title":"MIC-DKFZ/RegRCNN","url":"https://github.com/MIC-DKFZ/RegRCNN"},{"title":"MIC-DKFZ/DetectionAndRegression","url":"https://github.com/MIC-DKFZ/DetectionAndRegression"},{"title":"yczhang1017/SSD_resnet_pytorch","url":"https://github.com/yczhang1017/SSD_resnet_pytorch"},{"title":"waspinator/deep-learning-explorer","url":"https://github.com/waspinator/deep-learning-explorer"},{"title":"alexander-pv/maskrcnn_tf2","url":"https://github.com/alexander-pv/maskrcnn_tf2"},{"title":"maxfrei750/DeepParticleNet","url":"https://github.com/maxfrei750/DeepParticleNet"},{"title":"dvl-tum/motsynth-baselines","url":"https://github.com/dvl-tum/motsynth-baselines"},{"title":"bowu1004/instance_segmentation_RealSense","url":"https://github.com/bowu1004/instance_segmentation_RealSense"},{"title":"ssanyachetwani/Fashion-Trend-Detection-and-Recommendation-Model","url":"https://github.com/ssanyachetwani/Fashion-Trend-Detection-and-Recommendation-Model"},{"title":"pvdhove/owl-mask-rcnn","url":"https://github.com/pvdhove/owl-mask-rcnn"},{"title":"jylins/core-text","url":"https://github.com/jylins/core-text"},{"title":"SonginCV/MAF_HDA","url":"https://github.com/SonginCV/MAF_HDA"},{"title":"SonginCV/GMPHD_MAF","url":"https://github.com/SonginCV/GMPHD_MAF"},{"title":"ErikGDev/instance-segmentation","url":"https://github.com/ErikGDev/instance-segmentation"},{"title":"SonginCV/GMPHD_SAF","url":"https://github.com/SonginCV/GMPHD_SAF"},{"title":"deolipankaj/Stone_Detection_MRCNN","url":"https://github.com/deolipankaj/Stone_Detection_MRCNN"},{"title":"RaiyaniNirav/Mask-R-CNN-for-water-detection","url":"https://github.com/RaiyaniNirav/Mask-R-CNN-for-water-detection"},{"title":"CarstenIsert/DeepBurn","url":"https://github.com/CarstenIsert/DeepBurn"},{"title":"lukoucky/image_recommendation","url":"https://github.com/lukoucky/image_recommendation"},{"title":"lucylow/salty-wet-man","url":"https://github.com/lucylow/salty-wet-man"},{"title":"collectionslab/book-annotation-classification","url":"https://github.com/collectionslab/book-annotation-classification"},{"title":"Alexander-Whelan/Zeus","url":"https://github.com/Alexander-Whelan/Zeus"},{"title":"collectionslab/annotations-computervision","url":"https://github.com/collectionslab/annotations-computervision"},{"title":"collectionslab/Omniscribe","url":"https://github.com/collectionslab/Omniscribe"},{"title":"SfTI-Robotics/ROS-label-node","url":"https://github.com/SfTI-Robotics/ROS-label-node"},{"title":"houssemjebari/Fruit-Detection","url":"https://github.com/houssemjebari/Fruit-Detection"},{"title":"polospeter/TensorFlow-Advanced-Techniques-Specialization","url":"https://github.com/polospeter/TensorFlow-Advanced-Techniques-Specialization"},{"title":"NiravRaiyani/Mask-R-CNN-for-water-detection","url":"https://github.com/NiravRaiyani/Mask-R-CNN-for-water-detection"},{"title":"lixiaolei1982/DenseNet-base-Mask-RCNN-for-Human-Pose-Estimation","url":"https://github.com/lixiaolei1982/DenseNet-base-Mask-RCNN-for-Human-Pose-Estimation"},{"title":"o-evgeny/MRCNN_DeepFashion2","url":"https://github.com/o-evgeny/MRCNN_DeepFashion2"},{"title":"RajArPatra/Super-OCR","url":"https://github.com/RajArPatra/Super-OCR"},{"title":"xiuyu0000/papers_with_examples","url":"https://github.com/xiuyu0000/papers_with_examples/tree/main/maskrcnn"},{"title":"maxfrei750/FibeR-CNN","url":"https://github.com/maxfrei750/FibeR-CNN"},{"title":"scolocke/Traffic_Sign_ID_GTSRB_GTSDB","url":"https://github.com/scolocke/Traffic_Sign_ID_GTSRB_GTSDB"},{"title":"George-Ogden/Mask-RCNN","url":"https://github.com/George-Ogden/Mask-RCNN"},{"title":"delldu/MaskRCNN","url":"https://github.com/delldu/MaskRCNN"},{"title":"guanfuchen/py-faster-rcnn","url":"https://github.com/guanfuchen/py-faster-rcnn"},{"title":"pj1920/mask-r-cnn","url":"https://github.com/pj1920/mask-r-cnn"},{"title":"chuanqichen/deepcoaching","url":"https://github.com/chuanqichen/deepcoaching"},{"title":"Mrnoorsingh/car-parking","url":"https://github.com/Mrnoorsingh/car-parking"},{"title":"hellohaozheng/maskrcnn-mindspore","url":"https://github.com/hellohaozheng/maskrcnn-mindspore"},{"title":"noelcodes/Mask_RCNN","url":"https://github.com/noelcodes/Mask_RCNN"},{"title":"stanleycelestin1/AirsimDetectron","url":"https://github.com/stanleycelestin1/AirsimDetectron"},{"title":"fsafe/Capstone","url":"https://github.com/fsafe/Capstone"},{"title":"zhangchi9/Airbus_Ship_Detection","url":"https://github.com/zhangchi9/Airbus_Ship_Detection"},{"title":"chenwuperth/ClaRAN","url":"https://github.com/chenwuperth/ClaRAN"},{"title":"Rakeshvd/Semantic-Segmenation-of-MRI-scan-using-Mask-RCNN","url":"https://github.com/Rakeshvd/Semantic-Segmenation-of-MRI-scan-using-Mask-RCNN"},{"title":"Rakeshvd/Instance-Segmenation-of-MRI-scan-using-Mask-RCNN","url":"https://github.com/Rakeshvd/Instance-Segmenation-of-MRI-scan-using-Mask-RCNN"},{"title":"kdethoor/panoptictorch","url":"https://github.com/kdethoor/panoptictorch"},{"title":"quocdat32461997/Mask_RCNN","url":"https://github.com/quocdat32461997/Mask_RCNN"},{"title":"asyrovprog/cs230project","url":"https://github.com/asyrovprog/cs230project"},{"title":"StephenEkaputra/Mask_RCNN-TinyPascalVOC","url":"https://github.com/StephenEkaputra/Mask_RCNN-TinyPascalVOC"},{"title":"infini8-13/MaskRCNN_tryout","url":"https://github.com/infini8-13/MaskRCNN_tryout"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/MaskRCNN/maskrcnn_mobilenetv1"},{"title":"alexalm4190/Mask_RCNN-Vizzy_Hand","url":"https://github.com/alexalm4190/Mask_RCNN-Vizzy_Hand"},{"title":"jodumagpi/Xray-ObjSep-v1","url":"https://github.com/jodumagpi/Xray-ObjSep-v1"},{"title":"boom85423/Cartoon-style-Stickers-Generator","url":"https://github.com/boom85423/Cartoon-style-Stickers-Generator"},{"title":"jooyounghun/AI-Team-5","url":"https://github.com/jooyounghun/AI-Team-5"},{"title":"samsh19/ML_project","url":"https://github.com/samsh19/ML_project"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tinydarknet"},{"title":"jiajunhua/facebookresearch-Detectron","url":"https://github.com/jiajunhua/facebookresearch-Detectron"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/tinydarknet"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/MaskRCNN"},{"title":"AshishSingh2261/Pedestrian_Instance_Segmentation","url":"https://github.com/AshishSingh2261/Pedestrian_Instance_Segmentation"},{"title":"yangyucheng000/Mask-RCNN","url":"https://github.com/yangyucheng000/Mask-RCNN"},{"title":"alililia/ascend_maskrcnn_mobilenetv1","url":"https://github.com/alililia/ascend_maskrcnn_mobilenetv1"},{"title":"casiopa/Madrid_Rooftops","url":"https://github.com/casiopa/Madrid_Rooftops"},{"title":"BingkAI-B21CAP0161/C-Mask-Machine-Learning","url":"https://github.com/BingkAI-B21CAP0161/C-Mask-Machine-Learning"},{"title":"miaohua1982/simple_fasterrcnn_pytorch","url":"https://github.com/miaohua1982/simple_fasterrcnn_pytorch"},{"title":"DivJAth/DeepLearning5922","url":"https://github.com/DivJAth/DeepLearning5922"},{"title":"fdac18/ForensicImages","url":"https://github.com/fdac18/ForensicImages"},{"title":"phykn/film-defect-detection","url":"https://github.com/phykn/film-defect-detection"},{"title":"kbardool/mrcnn3","url":"https://github.com/kbardool/mrcnn3"},{"title":"ravenwritingdesk/py-faster-rcnn-master","url":"https://github.com/ravenwritingdesk/py-faster-rcnn-master"},{"title":"ColdNoodler/py-faster-rcnn-cuda10","url":"https://github.com/ColdNoodler/py-faster-rcnn-cuda10"},{"title":"baodi23/hourglass-facekeypoints-detection","url":"https://github.com/baodi23/hourglass-facekeypoints-detection"},{"title":"phtruongan/py-faster-rcnn-docker","url":"https://github.com/phtruongan/py-faster-rcnn-docker"},{"title":"krantirk/py-faster-rcnn","url":"https://github.com/krantirk/py-faster-rcnn"},{"title":"rh01/faster-rcnn","url":"https://github.com/rh01/faster-rcnn"},{"title":"beassssry/U","url":"https://github.com/beassssry/U"},{"title":"sunqiangxtcsun/faster-rcnn","url":"https://github.com/sunqiangxtcsun/faster-rcnn"},{"title":"lincaiming/py-faster-rcnn-windows","url":"https://github.com/lincaiming/py-faster-rcnn-windows"},{"title":"2023-MindSpore-4/Code9","url":"https://github.com/2023-MindSpore-4/Code9/tree/main/MaskRCNN"},{"title":"rickyHong/py-faster-rcnn-repl","url":"https://github.com/rickyHong/py-faster-rcnn-repl"},{"title":"BlackAngel1111/Fast-RCNN","url":"https://github.com/BlackAngel1111/Fast-RCNN"},{"title":"rh01/fast-rnn","url":"https://github.com/rh01/fast-rnn"},{"title":"Arthur-Shi/py-faster-rcnn","url":"https://github.com/Arthur-Shi/py-faster-rcnn"},{"title":"cokowpublic/Nuclei-Segmentation","url":"https://github.com/cokowpublic/Nuclei-Segmentation"},{"title":"evaristr/py-faster_rcnn","url":"https://github.com/evaristr/py-faster_rcnn"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/MaskRCNN"},{"title":"rickyHong/py-faster-rcnn-repl-cudnn5-support","url":"https://github.com/rickyHong/py-faster-rcnn-repl-cudnn5-support"},{"title":"soulguy/Faster-rcnn","url":"https://github.com/soulguy/Faster-rcnn"},{"title":"charlesYangM/py-faster-rcnn-80.28","url":"https://github.com/charlesYangM/py-faster-rcnn-80.28"},{"title":"busyboxs/What-I-have-star","url":"https://github.com/busyboxs/What-I-have-star"},{"title":"lincaiming/py-faster-rcnn-update","url":"https://github.com/lincaiming/py-faster-rcnn-update"},{"title":"xzabg/faster-rcnn-with-Caltech","url":"https://github.com/xzabg/faster-rcnn-with-Caltech"},{"title":"zhong110020/py-faster-rcnn","url":"https://github.com/zhong110020/py-faster-rcnn"},{"title":"sbetageri/MaskRCNN","url":"https://github.com/sbetageri/MaskRCNN"},{"title":"leochangzliao/OPBM","url":"https://github.com/leochangzliao/OPBM"},{"title":"qq330488563/TEST","url":"https://github.com/qq330488563/TEST"},{"title":"xunhen/py-faster-rcnn-wjc","url":"https://github.com/xunhen/py-faster-rcnn-wjc"},{"title":"GH3927/Mask-RCNN-applied-to-cranes","url":"https://github.com/GH3927/Mask-RCNN-applied-to-cranes"},{"title":"busyboxs/faster_rcnn_voc","url":"https://github.com/busyboxs/faster_rcnn_voc"},{"title":"TejasBajania/Mtech_pro","url":"https://github.com/TejasBajania/Mtech_pro"},{"title":"godspeedcurry/lung-nodule-detection","url":"https://github.com/godspeedcurry/lung-nodule-detection"},{"title":"paradisetechsoftsolutions/Deep-learning-model-using-Mask-R-CNN-for-predicting-AC-remote","url":"https://github.com/paradisetechsoftsolutions/Deep-learning-model-using-Mask-R-CNN-for-predicting-AC-remote"},{"title":"cwbabel/faster-cnn","url":"https://github.com/cwbabel/faster-cnn"},{"title":"jhihan/rsna_pneumonia_detection","url":"https://github.com/jhihan/rsna_pneumonia_detection"},{"title":"MindSpore-paper-code-2/code3","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/tinydarknet"},{"title":"jklife3/maskrcnn-impl","url":"https://github.com/jklife3/maskrcnn-impl"},{"title":"chihyanghsu0805/object_detection_yolo","url":"https://github.com/chihyanghsu0805/object_detection_yolo"},{"title":"Krupal09/MaskRCNN-Demo","url":"https://github.com/Krupal09/MaskRCNN-Demo"},{"title":"nikhithakarennagari/Git","url":"https://github.com/nikhithakarennagari/Git"},{"title":"nikhithakarennagari/1311","url":"https://github.com/nikhithakarennagari/1311"},{"title":"devsoft123/fast-cnn","url":"https://github.com/devsoft123/fast-cnn"},{"title":"GAOwy123/py-faster-rcnn","url":"https://github.com/GAOwy123/py-faster-rcnn"},{"title":"yj-littlesky/py-faster-rcnn","url":"https://github.com/yj-littlesky/py-faster-rcnn"},{"title":"elonashatri/pitch_mask_rcnn","url":"https://github.com/elonashatri/pitch_mask_rcnn"},{"title":"Qinhj07/ATOMCode","url":"https://github.com/Qinhj07/ATOMCode"},{"title":"ls5122/mask-rcnn","url":"https://github.com/ls5122/mask-rcnn"},{"title":"sunhui1234/haha","url":"https://github.com/sunhui1234/haha"},{"title":"xjnpark/ds","url":"https://github.com/xjnpark/ds"},{"title":"Biantian/MscProject","url":"https://github.com/Biantian/MscProject"},{"title":"TejasBajania/Mtech_thesis_project","url":"https://github.com/TejasBajania/Mtech_thesis_project"},{"title":"saehan-choi/pixellib_auto_labelling","url":"https://github.com/saehan-choi/pixellib_auto_labelling"},{"title":"yangyucheng000/maskrcnn_mobilenetv1","url":"https://github.com/yangyucheng000/maskrcnn_mobilenetv1"},{"title":"alililia/gpu_maskrcnn_mobilenetv1","url":"https://github.com/alililia/gpu_maskrcnn_mobilenetv1"},{"title":"Makunda/DeepLearningASL","url":"https://github.com/Makunda/DeepLearningASL"},{"title":"muyistarsky/MaskRCNN","url":"https://github.com/muyistarsky/MaskRCNN"},{"title":"2023-MindSpore-1/ms-code-207","url":"https://github.com/2023-MindSpore-1/ms-code-207"},{"title":"2023-MindSpore-1/ms-code-208","url":"https://github.com/2023-MindSpore-1/ms-code-208"},{"title":"UPCLJ/py-faster-rcnn","url":"https://github.com/UPCLJ/py-faster-rcnn"},{"title":"qilei123/pyfasterrcnn","url":"https://github.com/qilei123/pyfasterrcnn"},{"title":"MindSpore-paper-code-3/code3","url":"https://github.com/MindSpore-paper-code-3/code3/tree/main/faster_rcnn_dcn"},{"title":"leonardhan1979/fasterRCNN","url":"https://github.com/leonardhan1979/fasterRCNN"},{"title":"harrybolingot/mymaskrcnn","url":"https://github.com/harrybolingot/mymaskrcnn"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85849,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DiffusionInst-ResNet50","metrics":{"mask AP":"37.1"},"paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","paper_date":"2022-12-06","code_links":[{"title":"chenhaoxing/DiffusionInst","url":"https://github.com/chenhaoxing/DiffusionInst"},{"title":"alipay/diffusion-model-for-instance-segmentation","url":"https://github.com/alipay/diffusion-model-for-instance-segmentation"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85850,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"VirTex Mask R-CNN (ResNet-50-FPN)","metrics":{"AP50":"58.4","AP75":"39.7","mask AP":"36.9"},"paper_url":"https://arxiv.org/abs/2006.06666v3","paper_title":"VirTex: Learning Visual Representations from Textual Annotations","paper_date":"2020-06-11","code_links":[{"title":"kdexd/virtex","url":"https://github.com/kdexd/virtex"},{"title":"mattdeitke/cvpr-buzz","url":"https://github.com/mattdeitke/cvpr-buzz"},{"title":"rahulvigneswaran/longtail-buzz","url":"https://github.com/rahulvigneswaran/longtail-buzz"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85851,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"RDSNet (data aug)","metrics":{"AP50":"57.9%","AP75":"39.0%","APL":"51.6%","APM":"39.5%","APS":"16.4%","mask AP":"36.4%"},"paper_url":"https://arxiv.org/abs/1912.05070v1","paper_title":"RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation","paper_date":"2019-12-11","code_links":[{"title":"wangsr126/RDSNet","url":"https://github.com/wangsr126/RDSNet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85852,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MogaNet-T","metrics":{"mask AP":"35.8"},"paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_date":"2022-11-07","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85853,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"A2MIM (ResNet-50 2x)","metrics":{"mask AP":"34.9"},"paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","paper_date":"2022-05-27","code_links":[{"title":"open-mmlab/mmpretrain","url":"https://github.com/open-mmlab/mmpretrain"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"Westlake-AI/A2MIM","url":"https://github.com/Westlake-AI/A2MIM"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85854,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"E2EC DLA-34","metrics":{"AP50":"52.9","AP75":"35.9","mask AP":"33.8"},"paper_url":"https://arxiv.org/abs/2203.04074v1","paper_title":"E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation","paper_date":"2022-03-08","code_links":[{"title":"zhang-tao-whu/e2ec","url":"https://github.com/zhang-tao-whu/e2ec"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85855,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"FCIS+++  +OHEM","metrics":{"AP50":"54.5%","mask AP":"33.6%"},"paper_url":"http://arxiv.org/abs/1611.07709v2","paper_title":"Fully Convolutional Instance-aware Semantic Segmentation","paper_date":"2016-11-23","code_links":[{"title":"divamgupta/image-segmentation-keras","url":"https://github.com/divamgupta/image-segmentation-keras"},{"title":"msracver/FCIS","url":"https://github.com/msracver/FCIS"},{"title":"daijifeng001/TA-FCN","url":"https://github.com/daijifeng001/TA-FCN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85856,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask R-CNN (Bottleneck-injected ResNet-50, FPN)","metrics":{"mask AP":"33.6"},"paper_url":"https://arxiv.org/abs/2011.12913v2","paper_title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","paper_date":"2020-11-25","code_links":[{"title":"yoshitomo-matsubara/torchdistill","url":"https://github.com/yoshitomo-matsubara/torchdistill"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85857,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"PolarMask (ResNeXt-101-FPN)","metrics":{"AP50":"55.4%","AP75":"33.8%","APL":"46.3%","APM":"35.1%","APS":"15.5%","mask AP":"32.9%"},"paper_url":"https://arxiv.org/abs/1909.13226v4","paper_title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","paper_date":"2019-09-29","code_links":[{"title":"xieenze/PolarMask","url":"https://github.com/xieenze/PolarMask"},{"title":"KangJier/polarMask","url":"https://github.com/KangJier/polarMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85858,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"PolarMask (ResNet-101-FPN)","metrics":{"AP50":"51.9%","AP75":"31%","APL":"42.8%","APM":"32.4%","APS":"13.4%","mask AP":"30.4%"},"paper_url":"https://arxiv.org/abs/1909.13226v4","paper_title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","paper_date":"2019-09-29","code_links":[{"title":"xieenze/PolarMask","url":"https://github.com/xieenze/PolarMask"},{"title":"KangJier/polarMask","url":"https://github.com/KangJier/polarMask"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85859,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"YOLACT (ResNet-50-FPN)","metrics":{"mask AP":"29.8%"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85860,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"FCIS  +OHEM","metrics":{"AP50":"49.5%","APL":"50.0%","APM":"31.3%","APS":"7.1%","mask AP":"29.2%"},"paper_url":"http://arxiv.org/abs/1611.07709v2","paper_title":"Fully Convolutional Instance-aware Semantic Segmentation","paper_date":"2016-11-23","code_links":[{"title":"divamgupta/image-segmentation-keras","url":"https://github.com/divamgupta/image-segmentation-keras"},{"title":"msracver/FCIS","url":"https://github.com/msracver/FCIS"},{"title":"daijifeng001/TA-FCN","url":"https://github.com/daijifeng001/TA-FCN"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85861,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MultiPath Network","metrics":{"mask AP":"25.0%"},"paper_url":"http://arxiv.org/abs/1604.02135v2","paper_title":"A MultiPath Network for Object Detection","paper_date":"2016-04-07","code_links":[{"title":"facebookresearch/multipathnet","url":"https://github.com/facebookresearch/multipathnet"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85862,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"InternImage-H","metrics":{"AP50":"80.8","AP75":"62.2","APL":"70.3","APM":"58.9","APS":"41.0"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85863,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ResNeSt-200 (multi-scale)","metrics":{"AP50":"70.2","AP75":"51.5","APL":"60.6","APM":"49.6","APS":"30.0"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85864,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CenterMask + VoVNetV2-99 (multi-scale)","metrics":{"AP50":"66.2","AP75":"47.4","APS":"27.2"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85865,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CenterMask + VoVNetV2-57 (single-scale)","metrics":{"AP50":"60.8","APM":"41.7","APS":"19.4"},"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\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85866,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MNC","metrics":{"AP50":"44.3%"},"paper_url":"http://arxiv.org/abs/1512.04412v1","paper_title":"Instance-aware Semantic Segmentation via Multi-task Network Cascades","paper_date":"2015-12-14","code_links":[{"title":"daijifeng001/MNC","url":"https://github.com/daijifeng001/MNC"},{"title":"jfc4050/detect-to-track","url":"https://github.com/jfc4050/detect-to-track"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85867,"task":"Instance Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"ISDA (ResNet-50)","metrics":{"APL":"55.7"},"paper_url":"https://arxiv.org/abs/2202.12251v1","paper_title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","paper_date":"2022-02-23","code_links":[{"title":"yingkaining/isda","url":"https://github.com/yingkaining/isda"}],"metrics_order":"[\"mask AP\", \"AP50\", \"AP75\", \"APS\", \"APM\", \"APL\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}