{"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/semantic-diversity-learning-for-zero-shot","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","arxiv_id":"2105.05926","date":"2021-05-12","proceeding":"ICCV 2021 10","authors":["Avi Ben-Cohen","Nadav Zamir","Emanuel Ben Baruch","Itamar Friedman","Lihi Zelnik-Manor"],"abstract":"Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse labels. As challenging as this task is, it is an essential task to tackle since it represents many real-world cases, such as image retrieval of natural images. We argue that using a single embedding vector to represent an image, as commonly practiced, is not sufficient to rank both relevant seen and unseen labels accurately. This study introduces an end-to-end model training for multi-label zero-shot learning that supports semantic diversity of the images and labels. We propose to use an embedding matrix having principal embedding vectors trained using a tailored loss function. In addition, during training, we suggest up-weighting in the loss function image samples presenting higher semantic diversity to encourage the diversity of the embedding matrix. Extensive experiments show that our proposed method improves the zero-shot model's quality in tag-based image retrieval achieving SoTA results on several common datasets (NUS-Wide, COCO, Open Images).","url_abs":"https://arxiv.org/abs/2105.05926v1","url_pdf":"https://arxiv.org/pdf/2105.05926v1.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":"semantic-diversity-learning-for-zero-shot","repo_url":"https://github.com/Alibaba-MIIL/ZS_SDL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multi-label-zero-shot-learning","task_name":"Multi-label zero-shot learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-zero-shot-learning-on-nus-wide","task":"Multi-label zero-shot learning","dataset":"NUS-WIDE","model":"SDL","rank_in_archive_order":7,"of":10,"metrics":{"mAP":"25.9"},"uses_additional_data":false},{"leaderboard":"/sota/multi-label-zero-shot-learning-on-open-images","task":"Multi-label zero-shot learning","dataset":"Open Images V4","model":"ZS-SDL","rank_in_archive_order":3,"of":8,"metrics":{"MAP":"62.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.05926","atlas_url":"https://app.syntology.ai/?focus=2105.05926","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":"2105.05926"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.05926\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.05926"},"call":"get_concepts_for_paper(arxiv_id=\"2105.05926\")"}],"by_repo":[{"repo":"Alibaba-MIIL/ZS_SDL","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"52812698538c41485d7bdfe501ab41e884b6b17227db23e1a8c9d03236b7bacf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}