{"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/semi-supervised-deep-learning-by-metric","title":"Semi-supervised deep learning by metric embedding","arxiv_id":"1611.01449","date":"2016-11-04","proceeding":null,"authors":["Elad Hoffer","Nir Ailon"],"abstract":"Deep networks are successfully used as classification models yielding\nstate-of-the-art results when trained on a large number of labeled samples.\nThese models, however, are usually much less suited for semi-supervised\nproblems because of their tendency to overfit easily when trained on small\namounts of data. In this work we will explore a new training objective that is\ntargeting a semi-supervised regime with only a small subset of labeled data.\nThis criterion is based on a deep metric embedding over distance relations\nwithin the set of labeled samples, together with constraints over the\nembeddings of the unlabeled set. The final learned representations are\ndiscriminative in euclidean space, and hence can be used with subsequent\nnearest-neighbor classification using the labeled samples.","url_abs":"http://arxiv.org/abs/1611.01449v2","url_pdf":"http://arxiv.org/pdf/1611.01449v2.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":"semi-supervised-deep-learning-by-metric","repo_url":"https://github.com/eladhoffer/SemiSupContrast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}