{"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/zero-shot-learning-by-convex-combination-of","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","arxiv_id":"1312.5650","date":"2013-12-19","proceeding":null,"authors":["Mohammad Norouzi","Tomas Mikolov","Samy Bengio","Yoram Singer","Jonathon Shlens","Andrea Frome","Greg S. Corrado","Jeffrey Dean"],"abstract":"Several recent publications have proposed methods for mapping images into\ncontinuous semantic embedding spaces. In some cases the embedding space is\ntrained jointly with the image transformation. In other cases the semantic\nembedding space is established by an independent natural language processing\ntask, and then the image transformation into that space is learned in a second\nstage. Proponents of these image embedding systems have stressed their\nadvantages over the traditional \\nway{} classification framing of image\nunderstanding, particularly in terms of the promise for zero-shot learning --\nthe ability to correctly annotate images of previously unseen object\ncategories. In this paper, we propose a simple method for constructing an image\nembedding system from any existing \\nway{} image classifier and a semantic word\nembedding model, which contains the $\\n$ class labels in its vocabulary. Our\nmethod maps images into the semantic embedding space via convex combination of\nthe class label embedding vectors, and requires no additional training. We show\nthat this simple and direct method confers many of the advantages associated\nwith more complex image embedding schemes, and indeed outperforms state of the\nart methods on the ImageNet zero-shot learning task.","url_abs":"http://arxiv.org/abs/1312.5650v3","url_pdf":"http://arxiv.org/pdf/1312.5650v3.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":"zero-shot-learning-by-convex-combination-of","repo_url":"https://github.com/JudyYe/zero-shot-gcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"zero-shot-learning-by-convex-combination-of","repo_url":"https://github.com/ruotianluo/zsl-gcn-pth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-label-zero-shot-learning","task_name":"Multi-label zero-shot learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-0","task":"Few-Shot Image Classification","dataset":"ImageNet - 0-Shot","model":"ConSE","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"1.4%"},"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":"CONSE","rank_in_archive_order":8,"of":8,"metrics":{"MAP":"40.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1312.5650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1312.5650"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/JudyYe/zero-shot-gcn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ruotianluo/zsl-gcn-pth","reach":null}],"summary":{"unverified":3},"by_repo_kind":{},"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":3,"samples":[{"code_sha256_prefix":"a19debddc66fdc16","entry":"test_imagenet_zero","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a19debddc66fdc16"}},{"code_sha256_prefix":"99dfea413f8216e8","entry":"test_imagenet_zero","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"99dfea413f8216e8"}},{"code_sha256_prefix":"6b6e39f4d8304640","entry":"to_sparse","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6b6e39f4d8304640"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}