{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/probabilistic-and-or-attribute-grouping-for","title":"Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning","arxiv_id":"1806.02664","date":"2018-06-07","proceeding":null,"authors":["Yuval Atzmon","Gal Chechik"],"abstract":"In zero-shot learning (ZSL), a classifier is trained to recognize visual\nclasses without any image samples. Instead, it is given semantic information\nabout the class, like a textual description or a set of attributes. Learning\nfrom attributes could benefit from explicitly modeling structure of the\nattribute space. Unfortunately, learning of general structure from empirical\nsamples is hard with typical dataset sizes.\n  Here we describe LAGO, a probabilistic model designed to capture natural soft\nand-or relations across groups of attributes. We show how this model can be\nlearned end-to-end with a deep attribute-detection model. The soft group\nstructure can be learned from data jointly as part of the model, and can also\nreadily incorporate prior knowledge about groups if available. The soft and-or\nstructure succeeds to capture meaningful and predictive structures, improving\nthe accuracy of zero-shot learning on two of three benchmarks.\n  Finally, LAGO reveals a unified formulation over two ZSL approaches: DAP\n(Lampert et al., 2009) and ESZSL (Romera-Paredes & Torr, 2015). Interestingly,\ntaking only one singleton group for each attribute, introduces a new\nsoft-relaxation of DAP, that outperforms DAP by ~40.","url_abs":"http://arxiv.org/abs/1806.02664v2","url_pdf":"http://arxiv.org/pdf/1806.02664v2.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":"probabilistic-and-or-attribute-grouping-for","repo_url":"https://github.com/yuvalatzmon/LAGO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.02664","atlas_url":"https://app.syntology.ai/?focus=1806.02664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02664"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuvalatzmon/LAGO","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"a43aa1f4f4a3c26d","entry":"get_file","repo":"yuvalatzmon/LAGO","repo_kind":"listed","path":"zero_shot_src/ZStrain.py","file_url":"https://github.com/yuvalatzmon/LAGO/blob/HEAD/zero_shot_src/ZStrain.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a43aa1f4f4a3c26d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}