{"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/unsupervised-domain-adaptation-with-residual","title":"Unsupervised Domain Adaptation with Residual Transfer Networks","arxiv_id":"1602.04433","date":"2016-02-14","proceeding":"NeurIPS 2016 12","authors":["Mingsheng Long","Han Zhu","Jian-Min Wang","Michael. I. Jordan"],"abstract":"The recent success of deep neural networks relies on massive amounts of\nlabeled data. For a target task where labeled data is unavailable, domain\nadaptation can transfer a learner from a different source domain. In this\npaper, we propose a new approach to domain adaptation in deep networks that can\njointly learn adaptive classifiers and transferable features from labeled data\nin the source domain and unlabeled data in the target domain. We relax a\nshared-classifier assumption made by previous methods and assume that the\nsource classifier and target classifier differ by a residual function. We\nenable classifier adaptation by plugging several layers into deep network to\nexplicitly learn the residual function with reference to the target classifier.\nWe fuse features of multiple layers with tensor product and embed them into\nreproducing kernel Hilbert spaces to match distributions for feature\nadaptation. The adaptation can be achieved in most feed-forward models by\nextending them with new residual layers and loss functions, which can be\ntrained efficiently via back-propagation. Empirical evidence shows that the new\napproach outperforms state of the art methods on standard domain adaptation\nbenchmarks.","url_abs":"http://arxiv.org/abs/1602.04433v2","url_pdf":"http://arxiv.org/pdf/1602.04433v2.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":"unsupervised-domain-adaptation-with-residual","repo_url":"https://github.com/thuml/transfer-caffe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unsupervised-domain-adaptation-with-residual","repo_url":"https://github.com/kevinmusgrave/pytorch-adapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1602.04433","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}