{"task":"Panoptic Segmentation","dataset":"Mapillary val","metric_names":["PQ","mIoU","PQst","PQth"],"rows":[{"id":36869,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"OneFormer (DiNAT-L, single-scale)","metrics":{"PQ":"46.7","PQst":"54.9","PQth":"40.5","mIoU":"61.7"},"paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_date":"2022-11-10","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36870,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"OneFormer (ConvNeXt-L, single-scale)","metrics":{"PQ":"46.4","PQst":"54.0","PQth":"40.6","mIoU":"61.6"},"paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_date":"2022-11-10","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36871,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic FCN* (Swin-L, single-scale)","metrics":{"PQ":"45.7","PQst":"52.1","PQth":"40.8"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36872,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic-DeepLab (SWideRNet-(1, 1, 4.5), multi-scale)","metrics":{"PQ":"44.8","PQst":"51.9","PQth":"39.3","mIoU":"60.0"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36873,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Mask2Former + Intra-Batch Supervision (ResNet-50)","metrics":{"PQ":"42.2","PQst":"52.0","PQth":"34.9"},"paper_url":"https://arxiv.org/abs/2304.08222v1","paper_title":"Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images","paper_date":"2023-04-17","code_links":[{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36874,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Axial-DeepLab-L (multi-scale)","metrics":{"PQ":"41.1","PQst":"51.3","PQth":"33.4","mIoU":"58.4"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36875,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"EfficientPS","metrics":{"PQ":"40.6"},"paper_url":"https://arxiv.org/abs/2004.02307v3","paper_title":"EfficientPS: Efficient Panoptic Segmentation","paper_date":"2020-04-05","code_links":[{"title":"DeepSceneSeg/EfficientPS","url":"https://github.com/DeepSceneSeg/EfficientPS"},{"title":"vincrichard/EfficientPS","url":"https://github.com/vincrichard/EfficientPS"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36876,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic-DeepLab (X71)","metrics":{"PQ":"40.5"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36877,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"AdaptIS (ResNeXt-101)","metrics":{"PQ":"40.3","mIoU":"56.8"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36878,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic FCN* (ResNet-FPN)","metrics":{"PQ":"36.9","PQth":"32.9"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36879,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"JSIS-Net (ResNet-50)","metrics":{"PQ":"17.6"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36880,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"HRNet-OCR (Hierarchical Multi-Scale Attention)","metrics":{"PQ":"17.6"},"paper_url":"https://arxiv.org/abs/2005.10821v1","paper_title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","paper_date":"2020-05-21","code_links":[{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"NVIDIA/semantic-segmentation","url":"https://github.com/NVIDIA/semantic-segmentation"},{"title":"Song-Jingyu/runnable-PointPainting","url":"https://github.com/Song-Jingyu/runnable-PointPainting"},{"title":"Song-Jingyu/PointPainting","url":"https://github.com/Song-Jingyu/PointPainting"},{"title":"JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models","url":"https://github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models"},{"title":"valeoai/SemanticPalette","url":"https://github.com/valeoai/SemanticPalette"},{"title":"YeLyuUT/semantic_segmentation","url":"https://github.com/YeLyuUT/semantic_segmentation"},{"title":"ben-z-original/detectionhma","url":"https://github.com/ben-z-original/detectionhma"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":36881,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic FCN* (ResNet-50-FPN)","metrics":{"PQst":"42.3"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138614,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"OneFormer (DiNAT-L, single-scale)","metrics":{"PQ":"46.7","PQst":"54.9","PQth":"40.5","mIoU":"61.7"},"paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_date":"2022-11-10","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138615,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"OneFormer (ConvNeXt-L, single-scale)","metrics":{"PQ":"46.4","PQst":"54.0","PQth":"40.6","mIoU":"61.6"},"paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_date":"2022-11-10","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138616,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic FCN* (Swin-L, single-scale)","metrics":{"PQ":"45.7","PQst":"52.1","PQth":"40.8"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138617,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic-DeepLab (SWideRNet-(1, 1, 4.5), multi-scale)","metrics":{"PQ":"44.8","PQst":"51.9","PQth":"39.3","mIoU":"60.0"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138618,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Mask2Former + Intra-Batch Supervision (ResNet-50)","metrics":{"PQ":"42.2","PQst":"52.0","PQth":"34.9"},"paper_url":"https://arxiv.org/abs/2304.08222v1","paper_title":"Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images","paper_date":"2023-04-17","code_links":[{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138619,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Axial-DeepLab-L (multi-scale)","metrics":{"PQ":"41.1","PQst":"51.3","PQth":"33.4","mIoU":"58.4"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138620,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"EfficientPS","metrics":{"PQ":"40.6"},"paper_url":"https://arxiv.org/abs/2004.02307v3","paper_title":"EfficientPS: Efficient Panoptic Segmentation","paper_date":"2020-04-05","code_links":[{"title":"DeepSceneSeg/EfficientPS","url":"https://github.com/DeepSceneSeg/EfficientPS"},{"title":"vincrichard/EfficientPS","url":"https://github.com/vincrichard/EfficientPS"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138621,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic-DeepLab (X71)","metrics":{"PQ":"40.5"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138622,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"AdaptIS (ResNeXt-101)","metrics":{"PQ":"40.3","mIoU":"56.8"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138623,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic FCN* (ResNet-FPN)","metrics":{"PQ":"36.9","PQth":"32.9"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138624,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"JSIS-Net (ResNet-50)","metrics":{"PQ":"17.6"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138625,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"HRNet-OCR (Hierarchical Multi-Scale Attention)","metrics":{"PQ":"17.6"},"paper_url":"https://arxiv.org/abs/2005.10821v1","paper_title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","paper_date":"2020-05-21","code_links":[{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"NVIDIA/semantic-segmentation","url":"https://github.com/NVIDIA/semantic-segmentation"},{"title":"Song-Jingyu/runnable-PointPainting","url":"https://github.com/Song-Jingyu/runnable-PointPainting"},{"title":"Song-Jingyu/PointPainting","url":"https://github.com/Song-Jingyu/PointPainting"},{"title":"JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models","url":"https://github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models"},{"title":"valeoai/SemanticPalette","url":"https://github.com/valeoai/SemanticPalette"},{"title":"YeLyuUT/semantic_segmentation","url":"https://github.com/YeLyuUT/semantic_segmentation"},{"title":"ben-z-original/detectionhma","url":"https://github.com/ben-z-original/detectionhma"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":138626,"task":"Panoptic Segmentation","parent_task":"Semantic Segmentation","dataset":"Mapillary val","model_name":"Panoptic FCN* (ResNet-50-FPN)","metrics":{"PQst":"42.3"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141535,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"OneFormer (DiNAT-L, single-scale)","metrics":{"PQ":"46.7","PQst":"54.9","PQth":"40.5","mIoU":"61.7"},"paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_date":"2022-11-10","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141536,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"OneFormer (ConvNeXt-L, single-scale)","metrics":{"PQ":"46.4","PQst":"54.0","PQth":"40.6","mIoU":"61.6"},"paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_date":"2022-11-10","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141537,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Panoptic FCN* (Swin-L, single-scale)","metrics":{"PQ":"45.7","PQst":"52.1","PQth":"40.8"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141538,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Panoptic-DeepLab (SWideRNet-(1, 1, 4.5), multi-scale)","metrics":{"PQ":"44.8","PQst":"51.9","PQth":"39.3","mIoU":"60.0"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141539,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Mask2Former + Intra-Batch Supervision (ResNet-50)","metrics":{"PQ":"42.2","PQst":"52.0","PQth":"34.9"},"paper_url":"https://arxiv.org/abs/2304.08222v1","paper_title":"Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images","paper_date":"2023-04-17","code_links":[{"title":"DdeGeus/Mask2Former-IBS","url":"https://github.com/DdeGeus/Mask2Former-IBS"},{"title":"DdeGeus/PanopticFCN-IBS","url":"https://github.com/DdeGeus/PanopticFCN-IBS"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141540,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Axial-DeepLab-L (multi-scale)","metrics":{"PQ":"41.1","PQst":"51.3","PQth":"33.4","mIoU":"58.4"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141541,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"EfficientPS","metrics":{"PQ":"40.6"},"paper_url":"https://arxiv.org/abs/2004.02307v3","paper_title":"EfficientPS: Efficient Panoptic Segmentation","paper_date":"2020-04-05","code_links":[{"title":"DeepSceneSeg/EfficientPS","url":"https://github.com/DeepSceneSeg/EfficientPS"},{"title":"vincrichard/EfficientPS","url":"https://github.com/vincrichard/EfficientPS"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141542,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Panoptic-DeepLab (X71)","metrics":{"PQ":"40.5"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141543,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"AdaptIS (ResNeXt-101)","metrics":{"PQ":"40.3","mIoU":"56.8"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141544,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Panoptic FCN* (ResNet-FPN)","metrics":{"PQ":"36.9","PQth":"32.9"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141545,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"JSIS-Net (ResNet-50)","metrics":{"PQ":"17.6"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141546,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"HRNet-OCR (Hierarchical Multi-Scale Attention)","metrics":{"PQ":"17.6"},"paper_url":"https://arxiv.org/abs/2005.10821v1","paper_title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","paper_date":"2020-05-21","code_links":[{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"NVIDIA/semantic-segmentation","url":"https://github.com/NVIDIA/semantic-segmentation"},{"title":"Song-Jingyu/runnable-PointPainting","url":"https://github.com/Song-Jingyu/runnable-PointPainting"},{"title":"Song-Jingyu/PointPainting","url":"https://github.com/Song-Jingyu/PointPainting"},{"title":"JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models","url":"https://github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models"},{"title":"valeoai/SemanticPalette","url":"https://github.com/valeoai/SemanticPalette"},{"title":"YeLyuUT/semantic_segmentation","url":"https://github.com/YeLyuUT/semantic_segmentation"},{"title":"ben-z-original/detectionhma","url":"https://github.com/ben-z-original/detectionhma"}],"metrics_order":"[\"PQ\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":141547,"task":"Panoptic Segmentation","parent_task":null,"dataset":"Mapillary val","model_name":"Panoptic FCN* (ResNet-50-FPN)","metrics":{"PQst":"42.3"},"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\", \"mIoU\", \"PQst\", \"PQth\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}