{"task":"Panoptic Segmentation","dataset":"COCO test-dev","metric_names":["PQ","PQst","PQth"],"rows":[{"id":36904,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Mask DINO (single scale)","metrics":{"PQ":"59.5","PQst":"-","PQth":"-"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36905,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"kMaX-DeepLab (single-scale)","metrics":{"PQ":"58.5","PQst":"49.0","PQth":"64.8"},"paper_url":"https://arxiv.org/abs/2207.04044v5","paper_title":"kMaX-DeepLab: k-means Mask Transformer","paper_date":"2022-07-08","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"},{"title":"cy-xu/spatially_aware_ai","url":"https://github.com/cy-xu/spatially_aware_ai"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36906,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Mask2Former (Swin-L)","metrics":{"PQ":"58.3","PQst":"48.1","PQth":"65.1"},"paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","paper_date":"2021-12-02","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/Mask2Former","url":"https://github.com/facebookresearch/Mask2Former"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"nihalsid/mask2former","url":"https://github.com/nihalsid/mask2former"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/Mask2Former"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36907,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (Swin-L)","metrics":{"PQ":"56.2","PQst":"47.0","PQth":"62.3"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36908,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (PVTv2-B5)","metrics":{"PQ":"55.8","PQst":"46.5","PQth":"61.9"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36909,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"CMT-DeepLab (single-scale)","metrics":{"PQ":"55.7","PQst":"46.8","PQth":"61.6"},"paper_url":"https://arxiv.org/abs/2206.08948v1","paper_title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","paper_date":"2022-06-17","code_links":[{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/CMT"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36910,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"K-Net (Swin-L)","metrics":{"PQ":"55.2","PQst":"46.2","PQth":"61.2"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36911,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"MaskConver (ResNet50, single-scale)","metrics":{"PQ":"53.6","PQst":"58.9","PQth":"45.6"},"paper_url":"https://arxiv.org/abs/2312.06052v1","paper_title":"MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation","paper_date":"2023-12-11","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36912,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"MaskFormer (Swin-L)","metrics":{"PQ":"53.3","PQst":"44.5","PQth":"59.1"},"paper_url":"https://arxiv.org/abs/2107.06278v2","paper_title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","paper_date":"2021-07-13","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/MaskFormer","url":"https://github.com/facebookresearch/MaskFormer"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36913,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic FCN* (Swin-L)","metrics":{"PQ":"52.7","PQth":" 59.4"},"paper_url":"https://arxiv.org/abs/2012.00720v2","paper_title":"Fully Convolutional Networks for Panoptic Segmentation","paper_date":"2020-12-01","code_links":[{"title":"dvlab-research/panopticfcn","url":"https://github.com/dvlab-research/panopticfcn"},{"title":"yanwei-li/PanopticFCN","url":"https://github.com/yanwei-li/PanopticFCN"},{"title":"Jia-Research-Lab/PanopticFCN","url":"https://github.com/Jia-Research-Lab/PanopticFCN"},{"title":"dvlab-research/msad","url":"https://github.com/dvlab-research/msad"},{"title":"Jia-Research-Lab/MSAD","url":"https://github.com/Jia-Research-Lab/MSAD"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36914,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"REFINE (ResNeXt-101-DCN)","metrics":{"PQ":"51.5","PQst":"39.2","PQth":"59.6"},"paper_url":"https://sites.google.com/view/refine-aaai2021/home","paper_title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","paper_date":"2020-12-15","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36915,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"MaX-DeepLab-L (single-scale)","metrics":{"PQ":"51.3","PQst":"42.4","PQth":"57.2"},"paper_url":"https://arxiv.org/abs/2012.00759v3","paper_title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","paper_date":"2020-12-01","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"conradry/max-deeplab","url":"https://github.com/conradry/max-deeplab"},{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36916,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (ResNet-101)","metrics":{"PQ":"50.9","PQst":"43.0","PQth":"56.2"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36917,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (ResNet-50)","metrics":{"PQ":"50.2","PQst":"42.4","PQth":"55.3"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36918,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"DetectoRS (ResNeXt-101-64x4d, multi-scale)","metrics":{"PQ":"50","PQst":"37.2","PQth":"58.5"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36919,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"REFINE (ResNet-101-DCN)","metrics":{"PQ":"49.6","PQst":"37.7","PQth":"57.5"},"paper_url":"https://sites.google.com/view/refine-aaai2021/home","paper_title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","paper_date":"2020-12-15","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36920,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"SpatialFlow(ResNet-101-FPN)","metrics":{"PQ":"48.5","PQst":"37.9","PQth":"55.5"},"paper_url":"https://arxiv.org/abs/1910.08787v3","paper_title":"SpatialFlow: Bridging All Tasks for Panoptic Segmentation","paper_date":"2019-10-19","code_links":[{"title":"chensnathan/SpatialFlow","url":"https://github.com/chensnathan/SpatialFlow"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36921,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Ada-Segment (ResNet-101-DCN)","metrics":{"PQ":"48.5","PQst":"37.6","PQth":"55.7"},"paper_url":"https://arxiv.org/abs/2012.03603v1","paper_title":"Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation","paper_date":"2020-12-07","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36922,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"K-Net (R101-FPN-DCN)","metrics":{"PQ":"48.3","PQst":"39.7","PQth":"54"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36923,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"SOGNet (ResNet-101-FPN)","metrics":{"PQ":"47.8"},"paper_url":"https://arxiv.org/abs/1911.07527v1","paper_title":"SOGNet: Scene Overlap Graph Network for Panoptic Segmentation","paper_date":"2019-11-18","code_links":[{"title":"LaoYang1994/SOGNet","url":"https://github.com/LaoYang1994/SOGNet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36924,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic FCN*++ (DCN-101-FPN)","metrics":{"PQ":"47.5","PQst":"38.2","PQth":"53.7"},"paper_url":"https://arxiv.org/abs/2012.00720v2","paper_title":"Fully Convolutional Networks for Panoptic Segmentation","paper_date":"2020-12-01","code_links":[{"title":"dvlab-research/panopticfcn","url":"https://github.com/dvlab-research/panopticfcn"},{"title":"yanwei-li/PanopticFCN","url":"https://github.com/yanwei-li/PanopticFCN"},{"title":"Jia-Research-Lab/PanopticFCN","url":"https://github.com/Jia-Research-Lab/PanopticFCN"},{"title":"dvlab-research/msad","url":"https://github.com/dvlab-research/msad"},{"title":"Jia-Research-Lab/MSAD","url":"https://github.com/Jia-Research-Lab/MSAD"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36925,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"UPSNet (ResNet-101-FPN)","metrics":{"PQ":"46.6","PQst":"36.7","PQth":"53.2"},"paper_url":"http://arxiv.org/abs/1901.03784v2","paper_title":"UPSNet: A Unified Panoptic Segmentation Network","paper_date":"2019-01-12","code_links":[{"title":"uber-research/UPSNet","url":"https://github.com/uber-research/UPSNet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36926,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"OCFusion (ResNeXt-101-FPN)","metrics":{"PQ":"46.6","PQst":"35.7","PQth":"54.0"},"paper_url":"https://arxiv.org/abs/1906.05896v4","paper_title":"Learning Instance Occlusion for Panoptic Segmentation","paper_date":"2019-06-13","code_links":[{"title":"jlazarow/learning_instance_occlusion","url":"https://github.com/jlazarow/learning_instance_occlusion"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36927,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic-DeepLab (SWideRNet-[1, 1, 4], multi-scale)","metrics":{"PQ":"46.5","PQst":"38.2","PQth":"52.0"},"paper_url":"https://arxiv.org/abs/2011.11675v2","paper_title":"Scaling Wide Residual Networks for Panoptic Segmentation","paper_date":"2020-11-23","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36928,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AUNet (ResNext-152-FPN)","metrics":{"PQ":"46.5","PQst":"32.5","PQth":"55.8"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36929,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AUNet (ResNet-152-FPN)","metrics":{"PQ":"45.5","PQst":"31.6","PQth":"54.7"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36930,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AUNet (ResNet-101-FPN)","metrics":{"PQ":"45.2","PQst":"31.3","PQth":"54.4"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36931,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Axial-DeepLab-L (multi-scale)","metrics":{"PQ":"44.2","PQst":"36.8","PQth":"49.2"},"paper_url":"https://arxiv.org/abs/2003.07853v2","paper_title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","paper_date":"2020-03-17","code_links":[{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"csrhddlam/axial-deeplab","url":"https://github.com/csrhddlam/axial-deeplab"},{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"},{"title":"MartinGer/Stand-Alone-Axial-Attention","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36932,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Axial-DeepLab-L","metrics":{"PQ":"43.6","PQst":"35.6","PQth":"48.9"},"paper_url":"https://arxiv.org/abs/2003.07853v2","paper_title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","paper_date":"2020-03-17","code_links":[{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"csrhddlam/axial-deeplab","url":"https://github.com/csrhddlam/axial-deeplab"},{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"},{"title":"MartinGer/Stand-Alone-Axial-Attention","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36933,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AdaptIS (ResNeXt-101)","metrics":{"PQ":"42.8","PQst":"31.8","PQth":"50.1"},"paper_url":"https://arxiv.org/abs/1909.07829v1","paper_title":"AdaptIS: Adaptive Instance Selection Network","paper_date":"2019-09-17","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36934,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic-DeepLab (Xception-71)","metrics":{"PQ":"41.4","PQst":"35.9","PQth":"45.1"},"paper_url":"https://arxiv.org/abs/1911.10194v3","paper_title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","paper_date":"2019-11-22","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"bowenc0221/panoptic-deeplab","url":"https://github.com/bowenc0221/panoptic-deeplab"},{"title":"AbhinavAtrishi/semisupervised-multitask-learning","url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning"},{"title":"KenYu910645/perspective-aware-convolution","url":"https://github.com/KenYu910645/perspective-aware-convolution"},{"title":"JohnnyHopp/Panoptic-DeepLab-Mobilenetv2","url":"https://github.com/JohnnyHopp/Panoptic-DeepLab-Mobilenetv2"},{"title":"mistasse/modulom-panopticdeeplab","url":"https://github.com/mistasse/modulom-panopticdeeplab"},{"title":"sithu31296/panoptic-segmentation","url":"https://github.com/sithu31296/panoptic-segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36935,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic FPN","metrics":{"PQ":"40.9","PQst":"29.7","PQth":"48.3"},"paper_url":"http://arxiv.org/abs/1901.02446v2","paper_title":"Panoptic Feature Pyramid Networks","paper_date":"2019-01-08","code_links":[{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2"},{"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":"dajes/DensePose-TorchScript","url":"https://github.com/dajes/DensePose-TorchScript"},{"title":"Vishal-V/tf-models","url":"https://github.com/Vishal-V/tf-models"},{"title":"jlazarow/learning_instance_occlusion","url":"https://github.com/jlazarow/learning_instance_occlusion"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/resnext152_64x4d"},{"title":"Hernandope/keras_resnet_FPN_cifar10","url":"https://github.com/Hernandope/keras_resnet_FPN_cifar10"},{"title":"ashwath007/amenity-detection","url":"https://github.com/ashwath007/amenity-detection"},{"title":"ashwath007/aminity-detection","url":"https://github.com/ashwath007/aminity-detection"},{"title":"Shun14/panopticFPN-paddle","url":"https://github.com/Shun14/panopticFPN-paddle"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36936,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"TASCNet","metrics":{"PQ":"40.7","PQst":"31.0","PQth":"47.0"},"paper_url":"https://arxiv.org/abs/1812.01192v2","paper_title":"Learning to Fuse Things and Stuff","paper_date":"2018-12-04","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36937,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"EPSNet (ResNet-101-FPN)","metrics":{"PQ":"38.9","PQst":"31.0","PQth":"44.1"},"paper_url":"https://arxiv.org/abs/2003.10142v3","paper_title":"EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion","paper_date":"2020-03-23","code_links":[{"title":"neo85824/epsnet","url":"https://github.com/neo85824/epsnet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36938,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"COPS (ResNet-50)","metrics":{"PQ":"38.5","PQst":"34.8","PQth":"41.0"},"paper_url":"https://arxiv.org/abs/2106.03188v3","paper_title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","paper_date":"2021-06-06","code_links":[{"title":"LPMP/LPMP","url":"https://github.com/LPMP/LPMP"},{"title":"aabbas90/COPS","url":"https://github.com/aabbas90/COPS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36939,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"PCV (ResNet-50)","metrics":{"PQ":"37.7","PQst":"33.1","PQth":"40.7"},"paper_url":"https://arxiv.org/abs/2004.01849v1","paper_title":"Pixel Consensus Voting for Panoptic Segmentation","paper_date":"2020-04-04","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36940,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"GES Net","metrics":{"PQ":"33.7","PQst":"31.5","PQth":"35.1"},"paper_url":"https://arxiv.org/abs/1908.09108v4","paper_title":"Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into parts","paper_date":"2019-08-24","code_links":[{"title":"sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation","url":"https://github.com/sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation"},{"title":"sagieppel/Splitting-unfamiliar-objects-and-stuff-in-images-into-parts-using-neural-nets","url":"https://github.com/sagieppel/Splitting-unfamiliar-objects-and-stuff-in-images-into-parts-using-neural-nets"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36941,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"JSIS-Net","metrics":{"PQ":"27.2","PQst":"23.4","PQth":"29.6"},"paper_url":"http://arxiv.org/abs/1809.02110v2","paper_title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","paper_date":"2018-09-06","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138649,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Mask DINO (single scale)","metrics":{"PQ":"59.5","PQst":"-","PQth":"-"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138650,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"kMaX-DeepLab (single-scale)","metrics":{"PQ":"58.5","PQst":"49.0","PQth":"64.8"},"paper_url":"https://arxiv.org/abs/2207.04044v5","paper_title":"kMaX-DeepLab: k-means Mask Transformer","paper_date":"2022-07-08","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"},{"title":"cy-xu/spatially_aware_ai","url":"https://github.com/cy-xu/spatially_aware_ai"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138651,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Mask2Former (Swin-L)","metrics":{"PQ":"58.3","PQst":"48.1","PQth":"65.1"},"paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","paper_date":"2021-12-02","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/Mask2Former","url":"https://github.com/facebookresearch/Mask2Former"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"nihalsid/mask2former","url":"https://github.com/nihalsid/mask2former"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/Mask2Former"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138652,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (Swin-L)","metrics":{"PQ":"56.2","PQst":"47.0","PQth":"62.3"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138653,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (PVTv2-B5)","metrics":{"PQ":"55.8","PQst":"46.5","PQth":"61.9"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138654,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"CMT-DeepLab (single-scale)","metrics":{"PQ":"55.7","PQst":"46.8","PQth":"61.6"},"paper_url":"https://arxiv.org/abs/2206.08948v1","paper_title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","paper_date":"2022-06-17","code_links":[{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/CMT"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138655,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"K-Net (Swin-L)","metrics":{"PQ":"55.2","PQst":"46.2","PQth":"61.2"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138656,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"MaskConver (ResNet50, single-scale)","metrics":{"PQ":"53.6","PQst":"58.9","PQth":"45.6"},"paper_url":"https://arxiv.org/abs/2312.06052v1","paper_title":"MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation","paper_date":"2023-12-11","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138657,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"MaskFormer (Swin-L)","metrics":{"PQ":"53.3","PQst":"44.5","PQth":"59.1"},"paper_url":"https://arxiv.org/abs/2107.06278v2","paper_title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","paper_date":"2021-07-13","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/MaskFormer","url":"https://github.com/facebookresearch/MaskFormer"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138658,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic FCN* (Swin-L)","metrics":{"PQ":"52.7","PQth":" 59.4"},"paper_url":"https://arxiv.org/abs/2012.00720v2","paper_title":"Fully Convolutional Networks for Panoptic Segmentation","paper_date":"2020-12-01","code_links":[{"title":"dvlab-research/panopticfcn","url":"https://github.com/dvlab-research/panopticfcn"},{"title":"yanwei-li/PanopticFCN","url":"https://github.com/yanwei-li/PanopticFCN"},{"title":"Jia-Research-Lab/PanopticFCN","url":"https://github.com/Jia-Research-Lab/PanopticFCN"},{"title":"dvlab-research/msad","url":"https://github.com/dvlab-research/msad"},{"title":"Jia-Research-Lab/MSAD","url":"https://github.com/Jia-Research-Lab/MSAD"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138659,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"REFINE (ResNeXt-101-DCN)","metrics":{"PQ":"51.5","PQst":"39.2","PQth":"59.6"},"paper_url":"https://sites.google.com/view/refine-aaai2021/home","paper_title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","paper_date":"2020-12-15","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138660,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"MaX-DeepLab-L (single-scale)","metrics":{"PQ":"51.3","PQst":"42.4","PQth":"57.2"},"paper_url":"https://arxiv.org/abs/2012.00759v3","paper_title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","paper_date":"2020-12-01","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"conradry/max-deeplab","url":"https://github.com/conradry/max-deeplab"},{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138661,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (ResNet-101)","metrics":{"PQ":"50.9","PQst":"43.0","PQth":"56.2"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138662,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic SegFormer (ResNet-50)","metrics":{"PQ":"50.2","PQst":"42.4","PQth":"55.3"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138663,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"DetectoRS (ResNeXt-101-64x4d, multi-scale)","metrics":{"PQ":"50","PQst":"37.2","PQth":"58.5"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138664,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"REFINE (ResNet-101-DCN)","metrics":{"PQ":"49.6","PQst":"37.7","PQth":"57.5"},"paper_url":"https://sites.google.com/view/refine-aaai2021/home","paper_title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","paper_date":"2020-12-15","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138665,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"SpatialFlow(ResNet-101-FPN)","metrics":{"PQ":"48.5","PQst":"37.9","PQth":"55.5"},"paper_url":"https://arxiv.org/abs/1910.08787v3","paper_title":"SpatialFlow: Bridging All Tasks for Panoptic Segmentation","paper_date":"2019-10-19","code_links":[{"title":"chensnathan/SpatialFlow","url":"https://github.com/chensnathan/SpatialFlow"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138666,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Ada-Segment (ResNet-101-DCN)","metrics":{"PQ":"48.5","PQst":"37.6","PQth":"55.7"},"paper_url":"https://arxiv.org/abs/2012.03603v1","paper_title":"Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation","paper_date":"2020-12-07","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138667,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"K-Net (R101-FPN-DCN)","metrics":{"PQ":"48.3","PQst":"39.7","PQth":"54"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138668,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"SOGNet (ResNet-101-FPN)","metrics":{"PQ":"47.8"},"paper_url":"https://arxiv.org/abs/1911.07527v1","paper_title":"SOGNet: Scene Overlap Graph Network for Panoptic Segmentation","paper_date":"2019-11-18","code_links":[{"title":"LaoYang1994/SOGNet","url":"https://github.com/LaoYang1994/SOGNet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138669,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic FCN*++ (DCN-101-FPN)","metrics":{"PQ":"47.5","PQst":"38.2","PQth":"53.7"},"paper_url":"https://arxiv.org/abs/2012.00720v2","paper_title":"Fully Convolutional Networks for Panoptic Segmentation","paper_date":"2020-12-01","code_links":[{"title":"dvlab-research/panopticfcn","url":"https://github.com/dvlab-research/panopticfcn"},{"title":"yanwei-li/PanopticFCN","url":"https://github.com/yanwei-li/PanopticFCN"},{"title":"Jia-Research-Lab/PanopticFCN","url":"https://github.com/Jia-Research-Lab/PanopticFCN"},{"title":"dvlab-research/msad","url":"https://github.com/dvlab-research/msad"},{"title":"Jia-Research-Lab/MSAD","url":"https://github.com/Jia-Research-Lab/MSAD"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138670,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"UPSNet (ResNet-101-FPN)","metrics":{"PQ":"46.6","PQst":"36.7","PQth":"53.2"},"paper_url":"http://arxiv.org/abs/1901.03784v2","paper_title":"UPSNet: A Unified Panoptic Segmentation Network","paper_date":"2019-01-12","code_links":[{"title":"uber-research/UPSNet","url":"https://github.com/uber-research/UPSNet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138671,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"OCFusion (ResNeXt-101-FPN)","metrics":{"PQ":"46.6","PQst":"35.7","PQth":"54.0"},"paper_url":"https://arxiv.org/abs/1906.05896v4","paper_title":"Learning Instance Occlusion for Panoptic Segmentation","paper_date":"2019-06-13","code_links":[{"title":"jlazarow/learning_instance_occlusion","url":"https://github.com/jlazarow/learning_instance_occlusion"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138672,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic-DeepLab (SWideRNet-[1, 1, 4], multi-scale)","metrics":{"PQ":"46.5","PQst":"38.2","PQth":"52.0"},"paper_url":"https://arxiv.org/abs/2011.11675v2","paper_title":"Scaling Wide Residual Networks for Panoptic Segmentation","paper_date":"2020-11-23","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138673,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AUNet (ResNext-152-FPN)","metrics":{"PQ":"46.5","PQst":"32.5","PQth":"55.8"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138674,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AUNet (ResNet-152-FPN)","metrics":{"PQ":"45.5","PQst":"31.6","PQth":"54.7"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138675,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AUNet (ResNet-101-FPN)","metrics":{"PQ":"45.2","PQst":"31.3","PQth":"54.4"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138676,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Axial-DeepLab-L (multi-scale)","metrics":{"PQ":"44.2","PQst":"36.8","PQth":"49.2"},"paper_url":"https://arxiv.org/abs/2003.07853v2","paper_title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","paper_date":"2020-03-17","code_links":[{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"csrhddlam/axial-deeplab","url":"https://github.com/csrhddlam/axial-deeplab"},{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"},{"title":"MartinGer/Stand-Alone-Axial-Attention","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138677,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Axial-DeepLab-L","metrics":{"PQ":"43.6","PQst":"35.6","PQth":"48.9"},"paper_url":"https://arxiv.org/abs/2003.07853v2","paper_title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","paper_date":"2020-03-17","code_links":[{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"csrhddlam/axial-deeplab","url":"https://github.com/csrhddlam/axial-deeplab"},{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"},{"title":"MartinGer/Stand-Alone-Axial-Attention","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138678,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"AdaptIS (ResNeXt-101)","metrics":{"PQ":"42.8","PQst":"31.8","PQth":"50.1"},"paper_url":"https://arxiv.org/abs/1909.07829v1","paper_title":"AdaptIS: Adaptive Instance Selection Network","paper_date":"2019-09-17","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138679,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic-DeepLab (Xception-71)","metrics":{"PQ":"41.4","PQst":"35.9","PQth":"45.1"},"paper_url":"https://arxiv.org/abs/1911.10194v3","paper_title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","paper_date":"2019-11-22","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"bowenc0221/panoptic-deeplab","url":"https://github.com/bowenc0221/panoptic-deeplab"},{"title":"AbhinavAtrishi/semisupervised-multitask-learning","url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning"},{"title":"KenYu910645/perspective-aware-convolution","url":"https://github.com/KenYu910645/perspective-aware-convolution"},{"title":"JohnnyHopp/Panoptic-DeepLab-Mobilenetv2","url":"https://github.com/JohnnyHopp/Panoptic-DeepLab-Mobilenetv2"},{"title":"mistasse/modulom-panopticdeeplab","url":"https://github.com/mistasse/modulom-panopticdeeplab"},{"title":"sithu31296/panoptic-segmentation","url":"https://github.com/sithu31296/panoptic-segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138680,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"Panoptic FPN","metrics":{"PQ":"40.9","PQst":"29.7","PQth":"48.3"},"paper_url":"http://arxiv.org/abs/1901.02446v2","paper_title":"Panoptic Feature Pyramid Networks","paper_date":"2019-01-08","code_links":[{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2"},{"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":"dajes/DensePose-TorchScript","url":"https://github.com/dajes/DensePose-TorchScript"},{"title":"Vishal-V/tf-models","url":"https://github.com/Vishal-V/tf-models"},{"title":"jlazarow/learning_instance_occlusion","url":"https://github.com/jlazarow/learning_instance_occlusion"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/resnext152_64x4d"},{"title":"Hernandope/keras_resnet_FPN_cifar10","url":"https://github.com/Hernandope/keras_resnet_FPN_cifar10"},{"title":"ashwath007/amenity-detection","url":"https://github.com/ashwath007/amenity-detection"},{"title":"ashwath007/aminity-detection","url":"https://github.com/ashwath007/aminity-detection"},{"title":"Shun14/panopticFPN-paddle","url":"https://github.com/Shun14/panopticFPN-paddle"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138681,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"TASCNet","metrics":{"PQ":"40.7","PQst":"31.0","PQth":"47.0"},"paper_url":"https://arxiv.org/abs/1812.01192v2","paper_title":"Learning to Fuse Things and Stuff","paper_date":"2018-12-04","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138682,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"EPSNet (ResNet-101-FPN)","metrics":{"PQ":"38.9","PQst":"31.0","PQth":"44.1"},"paper_url":"https://arxiv.org/abs/2003.10142v3","paper_title":"EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion","paper_date":"2020-03-23","code_links":[{"title":"neo85824/epsnet","url":"https://github.com/neo85824/epsnet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138683,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"COPS (ResNet-50)","metrics":{"PQ":"38.5","PQst":"34.8","PQth":"41.0"},"paper_url":"https://arxiv.org/abs/2106.03188v3","paper_title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","paper_date":"2021-06-06","code_links":[{"title":"LPMP/LPMP","url":"https://github.com/LPMP/LPMP"},{"title":"aabbas90/COPS","url":"https://github.com/aabbas90/COPS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138684,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"PCV (ResNet-50)","metrics":{"PQ":"37.7","PQst":"33.1","PQth":"40.7"},"paper_url":"https://arxiv.org/abs/2004.01849v1","paper_title":"Pixel Consensus Voting for Panoptic Segmentation","paper_date":"2020-04-04","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138685,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"GES Net","metrics":{"PQ":"33.7","PQst":"31.5","PQth":"35.1"},"paper_url":"https://arxiv.org/abs/1908.09108v4","paper_title":"Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into parts","paper_date":"2019-08-24","code_links":[{"title":"sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation","url":"https://github.com/sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation"},{"title":"sagieppel/Splitting-unfamiliar-objects-and-stuff-in-images-into-parts-using-neural-nets","url":"https://github.com/sagieppel/Splitting-unfamiliar-objects-and-stuff-in-images-into-parts-using-neural-nets"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138686,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"COCO test-dev","model_name":"JSIS-Net","metrics":{"PQ":"27.2","PQst":"23.4","PQth":"29.6"},"paper_url":"http://arxiv.org/abs/1809.02110v2","paper_title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","paper_date":"2018-09-06","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141570,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask DINO (single scale)","metrics":{"PQ":"59.5","PQst":"-","PQth":"-"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141571,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"kMaX-DeepLab (single-scale)","metrics":{"PQ":"58.5","PQst":"49.0","PQth":"64.8"},"paper_url":"https://arxiv.org/abs/2207.04044v5","paper_title":"kMaX-DeepLab: k-means Mask Transformer","paper_date":"2022-07-08","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"},{"title":"cy-xu/spatially_aware_ai","url":"https://github.com/cy-xu/spatially_aware_ai"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141572,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Mask2Former (Swin-L)","metrics":{"PQ":"58.3","PQst":"48.1","PQth":"65.1"},"paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","paper_date":"2021-12-02","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/Mask2Former","url":"https://github.com/facebookresearch/Mask2Former"},{"title":"alibaba/EasyCV","url":"https://github.com/alibaba/EasyCV"},{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"nihalsid/mask2former","url":"https://github.com/nihalsid/mask2former"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/Mask2Former"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141573,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic SegFormer (Swin-L)","metrics":{"PQ":"56.2","PQst":"47.0","PQth":"62.3"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141574,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic SegFormer (PVTv2-B5)","metrics":{"PQ":"55.8","PQst":"46.5","PQth":"61.9"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141575,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"CMT-DeepLab (single-scale)","metrics":{"PQ":"55.7","PQst":"46.8","PQth":"61.6"},"paper_url":"https://arxiv.org/abs/2206.08948v1","paper_title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","paper_date":"2022-06-17","code_links":[{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"},{"title":"2024-MindSpore-1/Code7","url":"https://github.com/2024-MindSpore-1/Code7/tree/main/CMT"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141576,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"K-Net (Swin-L)","metrics":{"PQ":"55.2","PQst":"46.2","PQth":"61.2"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141577,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MaskConver (ResNet50, single-scale)","metrics":{"PQ":"53.6","PQst":"58.9","PQth":"45.6"},"paper_url":"https://arxiv.org/abs/2312.06052v1","paper_title":"MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation","paper_date":"2023-12-11","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141578,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MaskFormer (Swin-L)","metrics":{"PQ":"53.3","PQst":"44.5","PQth":"59.1"},"paper_url":"https://arxiv.org/abs/2107.06278v2","paper_title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","paper_date":"2021-07-13","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"facebookresearch/MaskFormer","url":"https://github.com/facebookresearch/MaskFormer"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141579,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic FCN* (Swin-L)","metrics":{"PQ":"52.7","PQth":" 59.4"},"paper_url":"https://arxiv.org/abs/2012.00720v2","paper_title":"Fully Convolutional Networks for Panoptic Segmentation","paper_date":"2020-12-01","code_links":[{"title":"dvlab-research/panopticfcn","url":"https://github.com/dvlab-research/panopticfcn"},{"title":"yanwei-li/PanopticFCN","url":"https://github.com/yanwei-li/PanopticFCN"},{"title":"Jia-Research-Lab/PanopticFCN","url":"https://github.com/Jia-Research-Lab/PanopticFCN"},{"title":"dvlab-research/msad","url":"https://github.com/dvlab-research/msad"},{"title":"Jia-Research-Lab/MSAD","url":"https://github.com/Jia-Research-Lab/MSAD"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141580,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"REFINE (ResNeXt-101-DCN)","metrics":{"PQ":"51.5","PQst":"39.2","PQth":"59.6"},"paper_url":"https://sites.google.com/view/refine-aaai2021/home","paper_title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","paper_date":"2020-12-15","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141581,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"MaX-DeepLab-L (single-scale)","metrics":{"PQ":"51.3","PQst":"42.4","PQth":"57.2"},"paper_url":"https://arxiv.org/abs/2012.00759v3","paper_title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","paper_date":"2020-12-01","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"conradry/max-deeplab","url":"https://github.com/conradry/max-deeplab"},{"title":"bytedance/kmax-deeplab","url":"https://github.com/bytedance/kmax-deeplab"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141582,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic SegFormer (ResNet-101)","metrics":{"PQ":"50.9","PQst":"43.0","PQth":"56.2"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141583,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic SegFormer (ResNet-50)","metrics":{"PQ":"50.2","PQst":"42.4","PQth":"55.3"},"paper_url":"https://arxiv.org/abs/2109.03814v4","paper_title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","paper_date":"2021-09-08","code_links":[{"title":"zhiqi-li/Panoptic-SegFormer","url":"https://github.com/zhiqi-li/Panoptic-SegFormer"},{"title":"claud1234/clft","url":"https://github.com/claud1234/clft"},{"title":"claud1234/fcn_transformer_object_segmentation","url":"https://github.com/claud1234/fcn_transformer_object_segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141584,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"DetectoRS (ResNeXt-101-64x4d, multi-scale)","metrics":{"PQ":"50","PQst":"37.2","PQth":"58.5"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141585,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"REFINE (ResNet-101-DCN)","metrics":{"PQ":"49.6","PQst":"37.7","PQth":"57.5"},"paper_url":"https://sites.google.com/view/refine-aaai2021/home","paper_title":"REFINE: Prediction Fusion Network for Panoptic Segmentation","paper_date":"2020-12-15","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141586,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SpatialFlow(ResNet-101-FPN)","metrics":{"PQ":"48.5","PQst":"37.9","PQth":"55.5"},"paper_url":"https://arxiv.org/abs/1910.08787v3","paper_title":"SpatialFlow: Bridging All Tasks for Panoptic Segmentation","paper_date":"2019-10-19","code_links":[{"title":"chensnathan/SpatialFlow","url":"https://github.com/chensnathan/SpatialFlow"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141587,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Ada-Segment (ResNet-101-DCN)","metrics":{"PQ":"48.5","PQst":"37.6","PQth":"55.7"},"paper_url":"https://arxiv.org/abs/2012.03603v1","paper_title":"Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation","paper_date":"2020-12-07","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141588,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"K-Net (R101-FPN-DCN)","metrics":{"PQ":"48.3","PQst":"39.7","PQth":"54"},"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":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141589,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"SOGNet (ResNet-101-FPN)","metrics":{"PQ":"47.8"},"paper_url":"https://arxiv.org/abs/1911.07527v1","paper_title":"SOGNet: Scene Overlap Graph Network for Panoptic Segmentation","paper_date":"2019-11-18","code_links":[{"title":"LaoYang1994/SOGNet","url":"https://github.com/LaoYang1994/SOGNet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141590,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic FCN*++ (DCN-101-FPN)","metrics":{"PQ":"47.5","PQst":"38.2","PQth":"53.7"},"paper_url":"https://arxiv.org/abs/2012.00720v2","paper_title":"Fully Convolutional Networks for Panoptic Segmentation","paper_date":"2020-12-01","code_links":[{"title":"dvlab-research/panopticfcn","url":"https://github.com/dvlab-research/panopticfcn"},{"title":"yanwei-li/PanopticFCN","url":"https://github.com/yanwei-li/PanopticFCN"},{"title":"Jia-Research-Lab/PanopticFCN","url":"https://github.com/Jia-Research-Lab/PanopticFCN"},{"title":"dvlab-research/msad","url":"https://github.com/dvlab-research/msad"},{"title":"Jia-Research-Lab/MSAD","url":"https://github.com/Jia-Research-Lab/MSAD"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141591,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"UPSNet (ResNet-101-FPN)","metrics":{"PQ":"46.6","PQst":"36.7","PQth":"53.2"},"paper_url":"http://arxiv.org/abs/1901.03784v2","paper_title":"UPSNet: A Unified Panoptic Segmentation Network","paper_date":"2019-01-12","code_links":[{"title":"uber-research/UPSNet","url":"https://github.com/uber-research/UPSNet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141592,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"OCFusion (ResNeXt-101-FPN)","metrics":{"PQ":"46.6","PQst":"35.7","PQth":"54.0"},"paper_url":"https://arxiv.org/abs/1906.05896v4","paper_title":"Learning Instance Occlusion for Panoptic Segmentation","paper_date":"2019-06-13","code_links":[{"title":"jlazarow/learning_instance_occlusion","url":"https://github.com/jlazarow/learning_instance_occlusion"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141593,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic-DeepLab (SWideRNet-[1, 1, 4], multi-scale)","metrics":{"PQ":"46.5","PQst":"38.2","PQth":"52.0"},"paper_url":"https://arxiv.org/abs/2011.11675v2","paper_title":"Scaling Wide Residual Networks for Panoptic Segmentation","paper_date":"2020-11-23","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141594,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"AUNet (ResNext-152-FPN)","metrics":{"PQ":"46.5","PQst":"32.5","PQth":"55.8"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141595,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"AUNet (ResNet-152-FPN)","metrics":{"PQ":"45.5","PQst":"31.6","PQth":"54.7"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141596,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"AUNet (ResNet-101-FPN)","metrics":{"PQ":"45.2","PQst":"31.3","PQth":"54.4"},"paper_url":"http://arxiv.org/abs/1812.03904v2","paper_title":"Attention-guided Unified Network for Panoptic Segmentation","paper_date":"2018-12-10","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141597,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Axial-DeepLab-L (multi-scale)","metrics":{"PQ":"44.2","PQst":"36.8","PQth":"49.2"},"paper_url":"https://arxiv.org/abs/2003.07853v2","paper_title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","paper_date":"2020-03-17","code_links":[{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"csrhddlam/axial-deeplab","url":"https://github.com/csrhddlam/axial-deeplab"},{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"},{"title":"MartinGer/Stand-Alone-Axial-Attention","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141598,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Axial-DeepLab-L","metrics":{"PQ":"43.6","PQst":"35.6","PQth":"48.9"},"paper_url":"https://arxiv.org/abs/2003.07853v2","paper_title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","paper_date":"2020-03-17","code_links":[{"title":"The-AI-Summer/self_attention","url":"https://github.com/The-AI-Summer/self_attention"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"csrhddlam/axial-deeplab","url":"https://github.com/csrhddlam/axial-deeplab"},{"title":"xiaofeng94/gmflownet","url":"https://github.com/xiaofeng94/gmflownet"},{"title":"MartinGer/Stand-Alone-Axial-Attention","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141599,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"AdaptIS (ResNeXt-101)","metrics":{"PQ":"42.8","PQst":"31.8","PQth":"50.1"},"paper_url":"https://arxiv.org/abs/1909.07829v1","paper_title":"AdaptIS: Adaptive Instance Selection Network","paper_date":"2019-09-17","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141600,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic-DeepLab (Xception-71)","metrics":{"PQ":"41.4","PQst":"35.9","PQth":"45.1"},"paper_url":"https://arxiv.org/abs/1911.10194v3","paper_title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","paper_date":"2019-11-22","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic"},{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"bowenc0221/panoptic-deeplab","url":"https://github.com/bowenc0221/panoptic-deeplab"},{"title":"AbhinavAtrishi/semisupervised-multitask-learning","url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning"},{"title":"KenYu910645/perspective-aware-convolution","url":"https://github.com/KenYu910645/perspective-aware-convolution"},{"title":"JohnnyHopp/Panoptic-DeepLab-Mobilenetv2","url":"https://github.com/JohnnyHopp/Panoptic-DeepLab-Mobilenetv2"},{"title":"mistasse/modulom-panopticdeeplab","url":"https://github.com/mistasse/modulom-panopticdeeplab"},{"title":"sithu31296/panoptic-segmentation","url":"https://github.com/sithu31296/panoptic-segmentation"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141601,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"Panoptic FPN","metrics":{"PQ":"40.9","PQst":"29.7","PQth":"48.3"},"paper_url":"http://arxiv.org/abs/1901.02446v2","paper_title":"Panoptic Feature Pyramid Networks","paper_date":"2019-01-08","code_links":[{"title":"facebookresearch/detectron2","url":"https://github.com/facebookresearch/detectron2"},{"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":"dajes/DensePose-TorchScript","url":"https://github.com/dajes/DensePose-TorchScript"},{"title":"Vishal-V/tf-models","url":"https://github.com/Vishal-V/tf-models"},{"title":"jlazarow/learning_instance_occlusion","url":"https://github.com/jlazarow/learning_instance_occlusion"},{"title":"code-implementation1/Code7","url":"https://github.com/code-implementation1/Code7/tree/main/resnext152_64x4d"},{"title":"Hernandope/keras_resnet_FPN_cifar10","url":"https://github.com/Hernandope/keras_resnet_FPN_cifar10"},{"title":"ashwath007/amenity-detection","url":"https://github.com/ashwath007/amenity-detection"},{"title":"ashwath007/aminity-detection","url":"https://github.com/ashwath007/aminity-detection"},{"title":"Shun14/panopticFPN-paddle","url":"https://github.com/Shun14/panopticFPN-paddle"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141602,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"TASCNet","metrics":{"PQ":"40.7","PQst":"31.0","PQth":"47.0"},"paper_url":"https://arxiv.org/abs/1812.01192v2","paper_title":"Learning to Fuse Things and Stuff","paper_date":"2018-12-04","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141603,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"EPSNet (ResNet-101-FPN)","metrics":{"PQ":"38.9","PQst":"31.0","PQth":"44.1"},"paper_url":"https://arxiv.org/abs/2003.10142v3","paper_title":"EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion","paper_date":"2020-03-23","code_links":[{"title":"neo85824/epsnet","url":"https://github.com/neo85824/epsnet"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141604,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"COPS (ResNet-50)","metrics":{"PQ":"38.5","PQst":"34.8","PQth":"41.0"},"paper_url":"https://arxiv.org/abs/2106.03188v3","paper_title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","paper_date":"2021-06-06","code_links":[{"title":"LPMP/LPMP","url":"https://github.com/LPMP/LPMP"},{"title":"aabbas90/COPS","url":"https://github.com/aabbas90/COPS"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141605,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"PCV (ResNet-50)","metrics":{"PQ":"37.7","PQst":"33.1","PQth":"40.7"},"paper_url":"https://arxiv.org/abs/2004.01849v1","paper_title":"Pixel Consensus Voting for Panoptic Segmentation","paper_date":"2020-04-04","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141606,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"GES Net","metrics":{"PQ":"33.7","PQst":"31.5","PQth":"35.1"},"paper_url":"https://arxiv.org/abs/1908.09108v4","paper_title":"Generator evaluator-selector net for panoptic image segmentation and splitting unfamiliar objects into parts","paper_date":"2019-08-24","code_links":[{"title":"sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation","url":"https://github.com/sagieppel/Generator-evaluator-selector-net-a-modular-approach-for-panoptic-segmentation"},{"title":"sagieppel/Splitting-unfamiliar-objects-and-stuff-in-images-into-parts-using-neural-nets","url":"https://github.com/sagieppel/Splitting-unfamiliar-objects-and-stuff-in-images-into-parts-using-neural-nets"}],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141607,"task":"Panoptic Segmentation","parent_task":null,"dataset":"COCO test-dev","model_name":"JSIS-Net","metrics":{"PQ":"27.2","PQst":"23.4","PQth":"29.6"},"paper_url":"http://arxiv.org/abs/1809.02110v2","paper_title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","paper_date":"2018-09-06","code_links":[],"metrics_order":"[\"PQ\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}