{"task":"Semantic Segmentation","dataset":"COCO (Common Objects in Context)","metric_names":["mIoU"],"rows":[{"id":35072,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"HyperSeg","metrics":{"mIoU":"77.2"},"paper_url":"https://arxiv.org/abs/2411.17606v2","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","paper_date":"2024-11-26","code_links":[{"title":"congvvc/HyperSeg","url":"https://github.com/congvvc/HyperSeg"}],"metrics_order":"[\"mIoU\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":35073,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"ViT-P (OneFormer, InternImage-H)","metrics":{"mIoU":"69.1"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35074,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"OneFormer (InternImage-H, emb_dim=1024, single-scale)","metrics":{"mIoU":"68.8"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35075,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"ViT-P (OneFormer, DiNAT-L)","metrics":{"mIoU":"68.8"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35076,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"OneFormer (DiNAT-L, single-scale)","metrics":{"mIoU":"68.1"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35077,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"OneFormer (Swin-L, single-scale)","metrics":{"mIoU":"67.4"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35078,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"Mask2Former (Swin-L, single-scale)","metrics":{"mIoU":"67.4"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35079,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"MaskFormer (Swin-L, single-scale)","metrics":{"mIoU":"64.8"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":35080,"task":"Semantic Segmentation","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"SegCLIP","metrics":{"mIoU":"26.5"},"paper_url":"https://arxiv.org/abs/2211.14813v2","paper_title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","paper_date":"2022-11-27","code_links":[{"title":"arrowluo/segclip","url":"https://github.com/arrowluo/segclip"}],"metrics_order":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136817,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"HyperSeg","metrics":{"mIoU":"77.2"},"paper_url":"https://arxiv.org/abs/2411.17606v2","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","paper_date":"2024-11-26","code_links":[{"title":"congvvc/HyperSeg","url":"https://github.com/congvvc/HyperSeg"}],"metrics_order":"[\"mIoU\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":136818,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"ViT-P (OneFormer, InternImage-H)","metrics":{"mIoU":"69.1"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136819,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"OneFormer (InternImage-H, emb_dim=1024, single-scale)","metrics":{"mIoU":"68.8"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136820,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"ViT-P (OneFormer, DiNAT-L)","metrics":{"mIoU":"68.8"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136821,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"OneFormer (DiNAT-L, single-scale)","metrics":{"mIoU":"68.1"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136822,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"OneFormer (Swin-L, single-scale)","metrics":{"mIoU":"67.4"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136823,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"Mask2Former (Swin-L, single-scale)","metrics":{"mIoU":"67.4"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136824,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"MaskFormer (Swin-L, single-scale)","metrics":{"mIoU":"64.8"},"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":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":136825,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"COCO (Common Objects in Context)","model_name":"SegCLIP","metrics":{"mIoU":"26.5"},"paper_url":"https://arxiv.org/abs/2211.14813v2","paper_title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","paper_date":"2022-11-27","code_links":[{"title":"arrowluo/segclip","url":"https://github.com/arrowluo/segclip"}],"metrics_order":"[\"mIoU\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}