{"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/attributes-as-operators-factorizing-unseen","title":"Attributes as Operators: Factorizing Unseen Attribute-Object Compositions","arxiv_id":"1803.09851","date":"2018-03-27","proceeding":"ECCV 2018 9","authors":["Tushar Nagarajan","Kristen Grauman"],"abstract":"We present a new approach to modeling visual attributes. Prior work casts\nattributes in a similar role as objects, learning a latent representation where\nproperties (e.g., sliced) are recognized by classifiers much in the way objects\n(e.g., apple) are. However, this common approach fails to separate the\nattributes observed during training from the objects with which they are\ncomposed, making it ineffectual when encountering new attribute-object\ncompositions. Instead, we propose to model attributes as operators. Our\napproach learns a semantic embedding that explicitly factors out attributes\nfrom their accompanying objects, and also benefits from novel regularizers\nexpressing attribute operators' effects (e.g., blunt should undo the effects of\nsharp). Not only does our approach align conceptually with the linguistic role\nof attributes as modifiers, but it also generalizes to recognize unseen\ncompositions of objects and attributes. We validate our approach on two\nchallenging datasets and demonstrate significant improvements over the\nstate-of-the-art. In addition, we show that not only can our model recognize\nunseen compositions robustly in an open-world setting, it can also generalize\nto compositions where objects themselves were unseen during training.","url_abs":"http://arxiv.org/abs/1803.09851v2","url_pdf":"http://arxiv.org/pdf/1803.09851v2.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":"attributes-as-operators-factorizing-unseen","repo_url":"https://github.com/Tushar-N/attributes-as-operators","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"compositional-zero-shot-learning","task_name":"Compositional Zero-Shot Learning"},{"task_slug":"multi-modal","task_name":"Image Retrieval with Multi-Modal Query"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-with-multi-modal-query-on-mit","task":"Image Retrieval with Multi-Modal Query","dataset":"MIT-States","model":"Attribute as Operator","rank_in_archive_order":5,"of":5,"metrics":{"Recall@1":"8.8","Recall@10":"39.1","Recall@5":"27.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.09851","atlas_url":"https://app.syntology.ai/?focus=1803.09851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09851"}},"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/Tushar-N/attributes-as-operators","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"88f1df65b04fc32f","entry":"flatten","repo":"Tushar-N/attributes-as-operators","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/Tushar-N/attributes-as-operators/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88f1df65b04fc32f"}},{"code_sha256_prefix":"18995d4e9ef69791","entry":"load_word_embeddings","repo":"Tushar-N/attributes-as-operators","repo_kind":"official","path":"models/models.py","file_url":"https://github.com/Tushar-N/attributes-as-operators/blob/HEAD/models/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18995d4e9ef69791"}},{"code_sha256_prefix":"331e1147542ad47b","entry":"train_svm","repo":"Tushar-N/attributes-as-operators","repo_kind":"official","path":"models/svm.py","file_url":"https://github.com/Tushar-N/attributes-as-operators/blob/HEAD/models/svm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"331e1147542ad47b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}