{"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/190510748","title":"Learning Smooth Representation for Unsupervised Domain Adaptation","arxiv_id":"1905.10748","date":"2019-05-26","proceeding":null,"authors":["Guanyu Cai","Lianghua He","Mengchu Zhou","Hesham Alhumade","Die Hu"],"abstract":"Typical adversarial-training-based unsupervised domain adaptation methods are vulnerable when the source and target datasets are highly-complex or exhibit a large discrepancy between their data distributions. Recently, several Lipschitz-constraint-based methods have been explored. The satisfaction of Lipschitz continuity guarantees a remarkable performance on a target domain. However, they lack a mathematical analysis of why a Lipschitz constraint is beneficial to unsupervised domain adaptation and usually perform poorly on large-scale datasets. In this paper, we take the principle of utilizing a Lipschitz constraint further by discussing how it affects the error bound of unsupervised domain adaptation. A connection between them is built and an illustration of how Lipschitzness reduces the error bound is presented. A \\textbf{local smooth discrepancy} is defined to measure Lipschitzness of a target distribution in a pointwise way. When constructing a deep end-to-end model, to ensure the effectiveness and stability of unsupervised domain adaptation, three critical factors are considered in our proposed optimization strategy, i.e., the sample amount of a target domain, dimension and batchsize of samples. Experimental results demonstrate that our model performs well on several standard benchmarks. Our ablation study shows that the sample amount of a target domain, the dimension and batchsize of samples indeed greatly impact Lipschitz-constraint-based methods' ability to handle large-scale datasets. Code is available at https://github.com/CuthbertCai/SRDA.","url_abs":"https://arxiv.org/abs/1905.10748v4","url_pdf":"https://arxiv.org/pdf/1905.10748v4.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":"190510748","repo_url":"https://github.com/CuthbertCai/SRDA","is_official":1,"mentioned_in_paper":1,"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":[{"leaderboard":"/sota/domain-adaptation-on-mnist-to-usps","task":"Domain Adaptation","dataset":"MNIST-to-USPS","model":"SRDA (RAN)","rank_in_archive_order":12,"of":14,"metrics":{"Accuracy":"94.76"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"SRDA (RAN)","rank_in_archive_order":40,"of":40,"metrics":{"Average Accuracy":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-svnh-to-mnist","task":"Domain Adaptation","dataset":"SVNH-to-MNIST","model":"SRDA (RAN)","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"98.91"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synsig-to-gtsrb","task":"Domain Adaptation","dataset":"SYNSIG-to-GTSRB","model":"SRDA (RAN)","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"93.61"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-usps-to-mnist","task":"Domain Adaptation","dataset":"USPS-to-MNIST","model":"SRDA (RAN)","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"95.03"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.10748","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}