{"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/minimal-entropy-correlation-alignment-for","title":"Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation","arxiv_id":"1711.10288","date":"2017-11-28","proceeding":"ICLR 2018 1","authors":["Pietro Morerio","Jacopo Cavazza","Vittorio Murino"],"abstract":"In this work, we face the problem of unsupervised domain adaptation with a\nnovel deep learning approach which leverages on our finding that entropy\nminimization is induced by the optimal alignment of second order statistics\nbetween source and target domains. We formally demonstrate this hypothesis and,\naiming at achieving an optimal alignment in practical cases, we adopt a more\nprincipled strategy which, differently from the current Euclidean approaches,\ndeploys alignment along geodesics. Our pipeline can be implemented by adding to\nthe standard classification loss (on the labeled source domain), a\nsource-to-target regularizer that is weighted in an unsupervised and\ndata-driven fashion. We provide extensive experiments to assess the superiority\nof our framework on standard domain and modality adaptation benchmarks.","url_abs":"http://arxiv.org/abs/1711.10288v1","url_pdf":"http://arxiv.org/pdf/1711.10288v1.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":"minimal-entropy-correlation-alignment-for","repo_url":"https://github.com/pmorerio/minimal-entropy-correlation-alignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10288","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}