{"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/unified-deep-supervised-domain-adaptation-and","title":"Unified Deep Supervised Domain Adaptation and Generalization","arxiv_id":"1709.10190","date":"2017-09-28","proceeding":"ICCV 2017 10","authors":["Saeid Motiian","Marco Piccirilli","Donald A. Adjeroh","Gianfranco Doretto"],"abstract":"This work provides a unified framework for addressing the problem of visual\nsupervised domain adaptation and generalization with deep models. The main idea\nis to exploit the Siamese architecture to learn an embedding subspace that is\ndiscriminative, and where mapped visual domains are semantically aligned and\nyet maximally separated. The supervised setting becomes attractive especially\nwhen only few target data samples need to be labeled. In this scenario,\nalignment and separation of semantic probability distributions is difficult\nbecause of the lack of data. We found that by reverting to point-wise\nsurrogates of distribution distances and similarities provides an effective\nsolution. In addition, the approach has a high speed of adaptation, which\nrequires an extremely low number of labeled target training samples, even one\nper category can be effective. The approach is extended to domain\ngeneralization. For both applications the experiments show very promising\nresults.","url_abs":"http://arxiv.org/abs/1709.10190v1","url_pdf":"http://arxiv.org/pdf/1709.10190v1.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":"unified-deep-supervised-domain-adaptation-and","repo_url":"https://github.com/YooJiHyeong/CCSA_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unified-deep-supervised-domain-adaptation-and","repo_url":"https://github.com/adapt-python/adapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unified-deep-supervised-domain-adaptation-and","repo_url":"https://github.com/samotiian/CCSA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"CCSA (Resnet-18)","rank_in_archive_order":96,"of":133,"metrics":{"Average Accuracy":"79.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.10190","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}