{"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":"/paper/open-vocabulary-semantic-segmentation-with-2","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","arxiv_id":"2212.04994","date":"2022-12-09","proceeding":"CVPR 2023 1","authors":["Jishnu Mukhoti","Tsung-Yu Lin","Omid Poursaeed","Rui Wang","Ashish Shah","Philip H. S. Torr","Ser-Nam Lim"],"abstract":"We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. Furthermore, we show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general improvement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.","url_abs":"https://arxiv.org/abs/2212.04994v1","url_pdf":"https://arxiv.org/pdf/2212.04994v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"open-vocabulary-semantic-segmentation-with-2","repo_url":"https://github.com/paulcouairon/diffcut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"open-vocabulary-semantic-segmentation-1","task_name":"Open-Vocabulary Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-2","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-150","model":"PACL","rank_in_archive_order":15,"of":23,"metrics":{"mIoU":"31.4"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-8","task":"Open Vocabulary Semantic Segmentation","dataset":"Cityscape-171","model":"PACL","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"38.8"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-1","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-59","model":"PACL","rank_in_archive_order":16,"of":24,"metrics":{"mIoU":"50.1"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-5","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20","model":"PACL","rank_in_archive_order":18,"of":20,"metrics":{"mIoU":"72.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.04994","atlas_url":"https://app.syntology.ai/?focus=2212.04994","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2212.04994"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.04994\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.04994"},"call":"get_concepts_for_paper(arxiv_id=\"2212.04994\")"}],"by_repo":[{"repo":"paulcouairon/diffcut","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.02842"],"harvested_for_calls":[{"arxiv_id":"2406.02842","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.02842"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.02842\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9975cb93202ad074d516caa91ac5284c63feda1ef245350458875411dc9acca3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}