{"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-via-semantic-similarity","title":"Zero-Shot Learning via Semantic Similarity Embedding","arxiv_id":"1509.04767","date":"2015-09-15","proceeding":"ICCV 2015 12","authors":["Ziming Zhang","Venkatesh Saligrama"],"abstract":"In this paper we consider a version of the zero-shot learning problem where\nseen class source and target domain data are provided. The goal during\ntest-time is to accurately predict the class label of an unseen target domain\ninstance based on revealed source domain side information (\\eg attributes) for\nunseen classes. Our method is based on viewing each source or target data as a\nmixture of seen class proportions and we postulate that the mixture patterns\nhave to be similar if the two instances belong to the same unseen class. This\nperspective leads us to learning source/target embedding functions that map an\narbitrary source/target domain data into a same semantic space where similarity\ncan be readily measured. We develop a max-margin framework to learn these\nsimilarity functions and jointly optimize parameters by means of cross\nvalidation. Our test results are compelling, leading to significant improvement\nin terms of accuracy on most benchmark datasets for zero-shot recognition.","url_abs":"http://arxiv.org/abs/1509.04767v2","url_pdf":"http://arxiv.org/pdf/1509.04767v2.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":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-2011-1","task":"Few-Shot Image Classification","dataset":"CUB-200-2011 - 0-Shot","model":"SSE-ReLU [?]","rank_in_archive_order":4,"of":5,"metrics":{"Top-1 Accuracy":"30.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.04767","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}