{"task":"Instance Segmentation","dataset":"ADE20K val","metric_names":["AP","APL","APM","APS"],"rows":[{"id":85924,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained)","metrics":{"AP":"44.2","APL":"64.3","APM":"49.9","APS":"23.7"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85925,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"OpenSeeD","metrics":{"AP":"42.6"},"paper_url":"https://arxiv.org/abs/2303.08131v3","paper_title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","paper_date":"2023-03-14","code_links":[{"title":"microsoft/X-Decoder","url":"https://github.com/microsoft/X-Decoder"},{"title":"idea-research/openseed","url":"https://github.com/idea-research/openseed"}],"metrics_order":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85926,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"ViT-P (OneFormer, DiNAT-L, single-scale, 1280x1280, COCO_pretrain)","metrics":{"AP":"40.7"},"paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","paper_date":"2025-05-26","code_links":[{"title":"sajjad-sh33/vit-p","url":"https://github.com/sajjad-sh33/vit-p"}],"metrics_order":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85927,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain)","metrics":{"AP":"40.2","APL":"59.7","APM":"44.4","APS":"19.2"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85928,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"X-Decoder (Davit-d5, Deform, single-scale, 1280x1280)","metrics":{"AP":"38.7","APL":"59.6","APM":"43.3","APS":"18.9"},"paper_url":"https://arxiv.org/abs/2212.11270v1","paper_title":"Generalized Decoding for Pixel, Image, and Language","paper_date":"2022-12-21","code_links":[{"title":"microsoft/X-Decoder","url":"https://github.com/microsoft/X-Decoder"}],"metrics_order":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85929,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"ViT-P (OneFormer, DiNAT-L, single-scale, 1280x1280)","metrics":{"AP":"37.8"},"paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","paper_date":"2025-05-26","code_links":[{"title":"sajjad-sh33/vit-p","url":"https://github.com/sajjad-sh33/vit-p"}],"metrics_order":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85930,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"OneFormer (DiNAT-L, single-scale)","metrics":{"AP":"36.0"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85931,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"OneFormer (Swin-L, single-scale)","metrics":{"AP":"35.9"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85932,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"X-Decoder (L)","metrics":{"AP":"35.8"},"paper_url":"https://arxiv.org/abs/2212.11270v1","paper_title":"Generalized Decoding for Pixel, Image, and Language","paper_date":"2022-12-21","code_links":[{"title":"microsoft/X-Decoder","url":"https://github.com/microsoft/X-Decoder"}],"metrics_order":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":85933,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"DiNAT-L (Mask2Former, single-scale)","metrics":{"AP":"35.4","APL":"55.5","APM":"39.0","APS":"16.3"},"paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","paper_date":"2022-09-29","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/Neighborhood-Attention-Transformer","url":"https://github.com/SHI-Labs/Neighborhood-Attention-Transformer"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/nat"},{"title":"shi-labs/natten","url":"https://github.com/shi-labs/natten"},{"title":"alexmehta/nac-tcn-tcns-with-causal-na","url":"https://github.com/alexmehta/nac-tcn-tcns-with-causal-na"},{"title":"MindSpore-scientific/code-8","url":"https://github.com/MindSpore-scientific/code-8/tree/main/MicAugment"},{"title":"MindSpore-scientific/code-10","url":"https://github.com/MindSpore-scientific/code-10/tree/main/MicAugment"}],"metrics_order":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85934,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"Mask2Former (Swin-L, single-scale)","metrics":{"AP":"34.9","APL":"54.7","APM":"40","APS":"16.3"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85935,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"Mask2Former (Swin-L + FAPN)","metrics":{"AP":"33.4","APL":"54.6","APM":"37.6","APS":"14.6"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85936,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"Mask2Former (ResNet50)","metrics":{"AP":"26.4","APS":"10.4"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":85937,"task":"Instance Segmentation","parent_task":null,"dataset":"ADE20K val","model_name":"Mask2Former (ResNet-50)","metrics":{"APL":"43.1","APM":"28.9"},"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":"[\"AP\", \"APL\", \"APM\", \"APS\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}