{"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/webly-supervised-concept-expansion-for","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","arxiv_id":"2202.02317","date":"2022-02-04","proceeding":null,"authors":["Amita Kamath","Christopher Clark","Tanmay Gupta","Eric Kolve","Derek Hoiem","Aniruddha Kembhavi"],"abstract":"General Purpose Vision (GPV) systems are models that are designed to solve a wide array of visual tasks without requiring architectural changes. Today, GPVs primarily learn both skills and concepts from large fully supervised datasets. Scaling GPVs to tens of thousands of concepts by acquiring data to learn each concept for every skill quickly becomes prohibitive. This work presents an effective and inexpensive alternative: learn skills from supervised datasets, learn concepts from web image search, and leverage a key characteristic of GPVs: the ability to transfer visual knowledge across skills. We use a dataset of 1M+ images spanning 10k+ visual concepts to demonstrate webly-supervised concept expansion for two existing GPVs (GPV-1 and VL-T5) on 3 benchmarks: 5 COCO-based datasets (80 primary concepts), a newly curated series of 5 datasets based on the OpenImages and VisualGenome repositories (~500 concepts), and the Web-derived dataset (10k+ concepts). We also propose a new architecture, GPV-2 that supports a variety of tasks -- from vision tasks like classification and localization to vision+language tasks like QA and captioning, to more niche ones like human-object interaction detection. GPV-2 benefits hugely from web data and outperforms GPV-1 and VL-T5 across these benchmarks. Our data, code, and web demo are available at https://prior.allenai.org/projects/gpv2.","url_abs":"https://arxiv.org/abs/2202.02317v2","url_pdf":"https://arxiv.org/pdf/2202.02317v2.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":[],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"object-categorization","task_name":"Object Categorization"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"vl-t5","method_name":"VL-T5"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-categorization-on-grit","task":"Object Categorization","dataset":"GRIT","model":"GPV-2","rank_in_archive_order":2,"of":4,"metrics":{"Categorization (ablation)":"54.7","Categorization (test)":"55.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-localization-on-grit","task":"Object Localization","dataset":"GRIT","model":"GPV-2","rank_in_archive_order":2,"of":3,"metrics":{"Localization (ablation)":"53.6","Localization (test)":"53.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-a-okvqa","task":"Visual Question Answering (VQA)","dataset":"A-OKVQA","model":"GPV-2","rank_in_archive_order":7,"of":15,"metrics":{"DA VQA Score":"40.7","MC Accuracy":"53.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-grit","task":"Visual Question Answering (VQA)","dataset":"GRIT","model":"GPV-2","rank_in_archive_order":2,"of":2,"metrics":{"VQA (ablation)":"63.5","VQA (test)":"63.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.02317","atlas_url":"https://app.syntology.ai/?focus=2202.02317","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":"2202.02317"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2202.02317\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2202.02317"},"call":"get_concepts_for_paper(arxiv_id=\"2202.02317\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"40c8c29994f2109398ee1c1dbc58528d1de76f09b2fce618309f39d9bb50ecc5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}