{"url":"/sota/semantic-segmentation-on-coco-1","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"COCO (Common Objects in Context)","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["mIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIoU":null}},"counts":{"rows":9,"rows_with_code":9,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"HyperSeg","metrics":{"mIoU":"77.2"},"uses_additional_data":true,"paper_date":"2024-11-26","paper":"/paper/hyperseg-towards-universal-visual","paper_url":"https://arxiv.org/abs/2411.17606v2","paper_title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","code":"https://github.com/congvvc/HyperSeg","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":10,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ViT-P (OneFormer, InternImage-H)","metrics":{"mIoU":"69.1"},"uses_additional_data":false,"paper_date":"2025-05-26","paper":"/paper/the-missing-point-in-vision-transformers-for","paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","code":"https://github.com/sajjad-sh33/vit-p","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"OneFormer (InternImage-H, emb_dim=1024, single-scale)","metrics":{"mIoU":"68.8"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"ViT-P (OneFormer, DiNAT-L)","metrics":{"mIoU":"68.8"},"uses_additional_data":false,"paper_date":"2025-05-26","paper":"/paper/the-missing-point-in-vision-transformers-for","paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","code":"https://github.com/sajjad-sh33/vit-p","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"OneFormer (DiNAT-L, single-scale)","metrics":{"mIoU":"68.1"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"OneFormer (Swin-L, single-scale)","metrics":{"mIoU":"67.4"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"Mask2Former (Swin-L, single-scale)","metrics":{"mIoU":"67.4"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"MaskFormer (Swin-L, single-scale)","metrics":{"mIoU":"64.8"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"SegCLIP","metrics":{"mIoU":"26.5"},"uses_additional_data":false,"paper_date":"2022-11-27","paper":"/paper/segclip-patch-aggregation-with-learnable","paper_url":"https://arxiv.org/abs/2211.14813v2","paper_title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","code":"https://github.com/arrowluo/segclip","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":21,"n_samples":30,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":11,"n_unverified":37,"n_samples":48,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}