{"url":"/sota/zero-shot-semantic-segmentation-on-coco-stuff","task":{"name":"Zero-Shot Semantic Segmentation","url":"/task/zero-shot-semantic-segmentation","note":null},"dataset":{"name":"COCO-Stuff","url":"/dataset/coco-stuff"},"category":"Computer Vision","categories":["Computer Vision"],"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":["Transductive Setting hIoU","Inductive Setting hIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Transductive Setting hIoU":null,"Inductive Setting hIoU":null}},"counts":{"rows":15,"rows_with_code":12,"rows_with_paper_page":15,"rows_dated":15,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"OTSeg+","metrics":{"Inductive Setting hIoU":"41.5","Transductive Setting hIoU":"49.8"},"uses_additional_data":false,"paper_date":"2024-03-21","paper":"/paper/otseg-multi-prompt-sinkhorn-attention-for","paper_url":"https://arxiv.org/abs/2403.14183v2","paper_title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","code":"https://github.com/cubeyoung/OTSeg","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":2,"model":"CLIP-RC","metrics":{"Inductive Setting hIoU":"41.2","Transductive Setting hIoU":"49.7"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/exploring-regional-clues-in-clip-for-zero","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Zhang_Exploring_Regional_Clues_in_CLIP_for_Zero-Shot_Semantic_Segmentation_CVPR_2024_paper.html","paper_title":"Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation","code":"https://github.com/Jittor/JSeg","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"OTSeg","metrics":{"Inductive Setting hIoU":"41.4","Transductive Setting hIoU":"49.5"},"uses_additional_data":false,"paper_date":"2024-03-21","paper":"/paper/otseg-multi-prompt-sinkhorn-attention-for","paper_url":"https://arxiv.org/abs/2403.14183v2","paper_title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","code":"https://github.com/cubeyoung/OTSeg","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":4,"model":"ZegCLIP","metrics":{"Inductive Setting hIoU":"40.8","Transductive Setting hIoU":"48.5"},"uses_additional_data":false,"paper_date":"2022-12-07","paper":"/paper/zegclip-towards-adapting-clip-for-zero-shot","paper_url":"https://arxiv.org/abs/2212.03588v3","paper_title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","code":"https://github.com/ZiqinZhou66/ZegCLIP","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MVP-SEG+","metrics":{"Inductive Setting hIoU":"-","Transductive Setting hIoU":"45.5"},"uses_additional_data":false,"paper_date":"2023-04-14","paper":"/paper/mvp-seg-multi-view-prompt-learning-for-open","paper_url":"https://arxiv.org/abs/2304.06957v1","paper_title":"MVP-SEG: Multi-View Prompt Learning for Open-Vocabulary Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"FreeSeg","metrics":{"Inductive Setting hIoU":"-","Transductive Setting hIoU":"45.3"},"uses_additional_data":false,"paper_date":"2022-09-27","paper":"/paper/freeseg-free-mask-from-interpretable","paper_url":"https://arxiv.org/abs/2209.13558v2","paper_title":"FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"MaskCLIP+","metrics":{"Inductive Setting hIoU":"-","Transductive Setting hIoU":"45.0"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/denseclip-extract-free-dense-labels-from-clip","paper_url":"https://arxiv.org/abs/2112.01071v2","paper_title":"Extract Free Dense Labels from CLIP","code":"https://github.com/chongzhou96/maskclip","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"zsseg","metrics":{"Inductive Setting hIoU":"36.3","Transductive Setting hIoU":"41.5"},"uses_additional_data":false,"paper_date":"2021-12-29","paper":"/paper/2112-14757","paper_url":"https://arxiv.org/abs/2112.14757v2","paper_title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","code":"https://github.com/mendelxu/zsseg.baseline","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"STRICT","metrics":{"Inductive Setting hIoU":"-","Transductive Setting hIoU":"34.8"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/a-closer-look-at-self-training-for-zero-label","paper_url":"https://arxiv.org/abs/2104.11692v1","paper_title":"A Closer Look at Self-training for Zero-Label Semantic Segmentation","code":"https://github.com/giuseppepastore10/STRICT","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SPNet","metrics":{"Inductive Setting hIoU":"14.0","Transductive Setting hIoU":"30.3"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/semantic-projection-network-for-zero-and-few","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Xian_Semantic_Projection_Network_for_Zero-_and_Few-Label_Semantic_Segmentation_CVPR_2019_paper.html","paper_title":"Semantic Projection Network for Zero- and Few-Label Semantic Segmentation","code":"https://github.com/subhc/SPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"CaGNet","metrics":{"Inductive Setting hIoU":"18.2","Transductive Setting hIoU":"19.5"},"uses_additional_data":false,"paper_date":"2020-08-16","paper":"/paper/context-aware-feature-generation-for-zero","paper_url":"https://arxiv.org/abs/2008.06893v1","paper_title":"Context-aware Feature Generation for Zero-shot Semantic Segmentation","code":"https://github.com/bcmi/CaGNet-Zero-Shot-Semantic-Segmentation","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"ZS5","metrics":{"Inductive Setting hIoU":"15.0","Transductive Setting hIoU":"16.2"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600817","paper_url":"https://arxiv.org/abs/1906.00817v2","paper_title":"Zero-Shot Semantic Segmentation","code":"https://github.com/valeoai/ZS3","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"DeOP","metrics":{"Inductive Setting hIoU":"38.2","Transductive Setting hIoU":"-"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/zero-shot-semantic-segmentation-with","paper_url":"https://arxiv.org/abs/2304.01198v2","paper_title":"Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network","code":"https://github.com/conghan0808/deop","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ZegFormer","metrics":{"Inductive Setting hIoU":"33.2","Transductive Setting hIoU":"-"},"uses_additional_data":false,"paper_date":"2021-12-15","paper":"/paper/decoupling-zero-shot-semantic-segmentation","paper_url":"https://arxiv.org/abs/2112.07910v2","paper_title":"Decoupling Zero-Shot Semantic Segmentation","code":"https://github.com/dingjiansw101/zegformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"SIGN","metrics":{"Inductive Setting hIoU":"20.9","Transductive Setting hIoU":"-"},"uses_additional_data":false,"paper_date":"2021-08-27","paper":"/paper/sign-spatial-information-incorporated","paper_url":"https://arxiv.org/abs/2108.12517v1","paper_title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":17,"n_unverified":2,"n_samples":19,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":26,"n_unverified":3,"n_samples":29,"n_pointer_only_licence":20,"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"}}}