{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/unsupervised-semantic-segmentation-with","name":"Unsupervised Semantic Segmentation with Language-image Pre-training","slug":"unsupervised-semantic-segmentation-with","description_markdown":"A segmentation task which does not utilise any human-level supervision for semantic segmentation except for a backbone which is initialised with features pre-trained with image-level labels.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":14,"papers_with_code":14,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-4","slug":"unsupervised-semantic-segmentation-with-4","dataset":"ADE20K","dataset_url":"/dataset/ade20k","rows_in_archive":13,"metrics":["Mean IoU (val)"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-10","slug":"unsupervised-semantic-segmentation-with-10","dataset":"COCO-Object","dataset_url":null,"rows_in_archive":12,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-3","slug":"unsupervised-semantic-segmentation-with-3","dataset":"Cityscapes val","dataset_url":"/dataset/cityscapes","rows_in_archive":12,"metrics":["mIoU","pixel accuracy"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-8","slug":"unsupervised-semantic-segmentation-with-8","dataset":"PASCAL Context-59","dataset_url":null,"rows_in_archive":12,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-9","slug":"unsupervised-semantic-segmentation-with-9","dataset":"COCO-Stuff-171","dataset_url":"/dataset/coco-stuff","rows_in_archive":12,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-11","slug":"unsupervised-semantic-segmentation-with-11","dataset":"PASCAL VOC","dataset_url":"/dataset/pascal-voc","rows_in_archive":10,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-7","slug":"unsupervised-semantic-segmentation-with-7","dataset":"PascalVOC-20","dataset_url":"/dataset/pascal-voc","rows_in_archive":10,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-1","slug":"unsupervised-semantic-segmentation-with-1","dataset":"COCO-Stuff-27","dataset_url":"/dataset/coco-stuff","rows_in_archive":4,"metrics":["mIoU","pixel accuracy"],"first_row_in_archive_order":{"model":"ReCo+","paper_title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","paper_url":"/paper/reco-retrieve-and-co-segment-for-zero-shot-1","paper_date":"2022-06-14","arxiv_id":"2206.07045","code_links":[{"title":"NoelShin/reco","url":"https://github.com/NoelShin/reco"},{"title":"noelshin/namedmask","url":"https://github.com/noelshin/namedmask"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-12","slug":"unsupervised-semantic-segmentation-with-12","dataset":"PASCAL Context-60","dataset_url":null,"rows_in_archive":4,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CorrCLIP","paper_title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","paper_url":"/paper/corrclip-reconstructing-correlations-in-clip","paper_date":"2024-11-15","arxiv_id":"2411.10086","code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}],"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-2","slug":"unsupervised-semantic-segmentation-with-2","dataset":"KITTI-STEP","dataset_url":"/dataset/kitti-step","rows_in_archive":3,"metrics":["mIoU","pixel accuracy"],"first_row_in_archive_order":{"model":"ReCo+","paper_title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","paper_url":"/paper/reco-retrieve-and-co-segment-for-zero-shot-1","paper_date":"2022-06-14","arxiv_id":"2206.07045","code_links":[{"title":"NoelShin/reco","url":"https://github.com/NoelShin/reco"},{"title":"noelshin/namedmask","url":"https://github.com/noelshin/namedmask"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-5","slug":"unsupervised-semantic-segmentation-with-5","dataset":"COCO (Common Objects in Context)","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["Mean IoU (val)"],"first_row_in_archive_order":{"model":"CLIPpy ViT-B","paper_title":"Perceptual Grouping in Contrastive Vision-Language Models","paper_url":"/paper/perceptual-grouping-in-vision-language-models","paper_date":"2022-10-18","arxiv_id":"2210.09996","code_links":[{"title":"kahnchana/clippy","url":"https://github.com/kahnchana/clippy"},{"title":"jongwoopark7978/LVNet","url":"https://github.com/jongwoopark7978/LVNet"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-6","slug":"unsupervised-semantic-segmentation-with-6","dataset":"PASCAL VOC 2007","dataset_url":"/dataset/pascal-voc-2007","rows_in_archive":1,"metrics":["Mean IoU (val)"],"first_row_in_archive_order":{"model":"CLIPpy ViT-B","paper_title":"Perceptual Grouping in Contrastive Vision-Language Models","paper_url":"/paper/perceptual-grouping-in-vision-language-models","paper_date":"2022-10-18","arxiv_id":"2210.09996","code_links":[{"title":"kahnchana/clippy","url":"https://github.com/kahnchana/clippy"},{"title":"jongwoopark7978/LVNet","url":"https://github.com/jongwoopark7978/LVNet"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213},{"url":"/dataset/coco-stuff","name":"COCO-Stuff","full_name":"Common Objects in COntext-stuff","num_papers_in_archive":338},{"url":"/dataset/pascal-voc","name":"PASCAL VOC","full_name":"PASCAL Visual Object Classes Challenge","num_papers_in_archive":198},{"url":"/dataset/pascal-voc-2007","name":"PASCAL VOC 2007","full_name":"PASCAL VOC 2007","num_papers_in_archive":126},{"url":"/dataset/kitti-step","name":"KITTI-STEP","full_name":"","num_papers_in_archive":24}],"subtasks":[],"parent_tasks":[{"url":"/task/unsupervised-semantic-segmentation","name":"Unsupervised Semantic Segmentation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":14,"of":14,"of_with_code":14,"tagged_in_all":14,"counts":{"archive_papers_tagged":14,"with_a_code_link":14,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/groupvit-semantic-segmentation-emerges-from","slug":"groupvit-semantic-segmentation-emerges-from","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","date":"2022-02-22","arxiv_id":"2202.11094","repositories_listed":6,"syntology":null},{"url":"/paper/perceptual-grouping-in-vision-language-models","slug":"perceptual-grouping-in-vision-language-models","title":"Perceptual Grouping in Contrastive Vision-Language Models","date":"2022-10-18","arxiv_id":"2210.09996","repositories_listed":2,"syntology":null},{"url":"/paper/reco-retrieve-and-co-segment-for-zero-shot-1","slug":"reco-retrieve-and-co-segment-for-zero-shot-1","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","date":"2022-06-14","arxiv_id":"2206.07045","repositories_listed":2,"syntology":null},{"url":"/paper/textregion-text-aligned-region-tokens-from","slug":"textregion-text-aligned-region-tokens-from","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","date":"2025-05-29","arxiv_id":"2505.23769","repositories_listed":1,"syntology":null},{"url":"/paper/cosmos-cross-modality-self-distillation-for","slug":"cosmos-cross-modality-self-distillation-for","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","date":"2024-12-02","arxiv_id":"2412.01814","repositories_listed":1,"syntology":null},{"url":"/paper/itaclip-boosting-training-free-semantic","slug":"itaclip-boosting-training-free-semantic","title":"ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements","date":"2024-11-18","arxiv_id":"2411.12044","repositories_listed":1,"syntology":null},{"url":"/paper/corrclip-reconstructing-correlations-in-clip","slug":"corrclip-reconstructing-correlations-in-clip","title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","date":"2024-11-15","arxiv_id":"2411.10086","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/corrclip-reconstructing-correlations-in-clip#ran","syntology_url":"https://syntology.ai/paper/2411.10086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10086"}},"official":{"repos":["zdk258/CorrCLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/harnessing-vision-foundation-models-for-high","slug":"harnessing-vision-foundation-models-for-high","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","date":"2024-11-14","arxiv_id":"2411.09219","repositories_listed":1,"syntology":null},{"url":"/paper/proxyclip-proxy-attention-improves-clip-for","slug":"proxyclip-proxy-attention-improves-clip-for","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","date":"2024-08-09","arxiv_id":"2408.04883","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/proxyclip-proxy-attention-improves-clip-for#ran","syntology_url":"https://syntology.ai/paper/2408.04883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04883"}},"official":{"repos":["mc-lan/proxyclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ttd-text-tag-self-distillation-enhancing","slug":"ttd-text-tag-self-distillation-enhancing","title":"TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias","date":"2024-03-30","arxiv_id":"2404.00384","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ttd-text-tag-self-distillation-enhancing#ran","syntology_url":"https://syntology.ai/paper/2404.00384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00384"}},"official":{"repos":["shjo-april/TTD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tagalign-improving-vision-language-alignment","slug":"tagalign-improving-vision-language-alignment","title":"TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification","date":"2023-12-21","arxiv_id":"2312.14149","repositories_listed":1,"syntology":null},{"url":"/paper/tagclip-a-local-to-global-framework-to","slug":"tagclip-a-local-to-global-framework-to","title":"TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training","date":"2023-12-20","arxiv_id":"2312.12828","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generate-text-grounded-mask-for","slug":"learning-to-generate-text-grounded-mask-for","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","date":"2022-12-01","arxiv_id":"2212.00785","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-to-generate-text-grounded-mask-for#ran","syntology_url":"https://syntology.ai/paper/2212.00785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00785"}},"official":{"repos":["kakaobrain/tcl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/denseclip-extract-free-dense-labels-from-clip","slug":"denseclip-extract-free-dense-labels-from-clip","title":"Extract Free Dense Labels from CLIP","date":"2021-12-02","arxiv_id":"2112.01071","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-10","since_archive":"/sota/unsupervised-semantic-segmentation-with-10#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-8","since_archive":"/sota/unsupervised-semantic-segmentation-with-8#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-9","since_archive":"/sota/unsupervised-semantic-segmentation-with-9#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/unsupervised-semantic-segmentation-with/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/unsupervised-semantic-segmentation-with/papers/ran/1","json":"/task/unsupervised-semantic-segmentation-with/papers/ran/1.json","rows":4}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"027957576ae155522baff2a1d61e1c46b7d6fffacab9cd9fd003a305cf6b86e0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}