{"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/perceptual-grouping-in-vision-language-models","title":"Perceptual Grouping in Contrastive Vision-Language Models","arxiv_id":"2210.09996","date":"2022-10-18","proceeding":"ICCV 2023 1","authors":["Kanchana Ranasinghe","Brandon McKinzie","Sachin Ravi","Yinfei Yang","Alexander Toshev","Jonathon Shlens"],"abstract":"Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding an image, however, is not just about understanding what content resides within an image, but importantly, where that content resides. In this work we examine how well vision-language models are able to understand where objects reside within an image and group together visually related parts of the imagery. We demonstrate how contemporary vision and language representation learning models based on contrastive losses and large web-based data capture limited object localization information. We propose a minimal set of modifications that results in models that uniquely learn both semantic and spatial information. We measure this performance in terms of zero-shot image recognition, unsupervised bottom-up and top-down semantic segmentations, as well as robustness analyses. We find that the resulting model achieves state-of-the-art results in terms of unsupervised segmentation, and demonstrate that the learned representations are uniquely robust to spurious correlations in datasets designed to probe the causal behavior of vision models.","url_abs":"https://arxiv.org/abs/2210.09996v3","url_pdf":"https://arxiv.org/pdf/2210.09996v3.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":"perceptual-grouping-in-vision-language-models","repo_url":"https://github.com/jongwoopark7978/LVNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"perceptual-grouping-in-vision-language-models","repo_url":"https://github.com/kahnchana/clippy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation-with","task_name":"Unsupervised Semantic Segmentation with Language-image Pre-training"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-4","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"ADE20K","model":"CLIPpy ViT-B","rank_in_archive_order":9,"of":13,"metrics":{"Mean IoU (val)":"13.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-5","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"COCO (Common Objects in Context)","model":"CLIPpy ViT-B","rank_in_archive_order":1,"of":1,"metrics":{"Mean IoU (val)":"25.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-3","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"Cityscapes val","model":"CLIPpy ViT-B","rank_in_archive_order":11,"of":12,"metrics":{"mIoU":"18.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-6","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PASCAL VOC 2007","model":"CLIPpy ViT-B","rank_in_archive_order":1,"of":1,"metrics":{"Mean IoU (val)":"52.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.09996","atlas_url":"https://app.syntology.ai/?focus=2210.09996","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":"2210.09996"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.09996\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.09996"},"call":"get_concepts_for_paper(arxiv_id=\"2210.09996\")"}],"by_repo":[{"repo":"jongwoopark7978/LVNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.09396"],"harvested_for_calls":[{"arxiv_id":"2406.09396","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.09396"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.09396\")"}]},{"repo":"kahnchana/clippy","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"caa1d089dc0a042d71abf76d9633c2410edc8dd556686a6583764fc57b3aa0a8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}