{"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/importance-weighted-adversarial-nets-for","title":"Importance Weighted Adversarial Nets for Partial Domain Adaptation","arxiv_id":"1803.09210","date":"2018-03-25","proceeding":"CVPR 2018 6","authors":["Jing Zhang","Zewei Ding","Wanqing Li","Philip Ogunbona"],"abstract":"This paper proposes an importance weighted adversarial nets-based method for\nunsupervised domain adaptation, specific for partial domain adaptation where\nthe target domain has less number of classes compared to the source domain.\nPrevious domain adaptation methods generally assume the identical label spaces,\nsuch that reducing the distribution divergence leads to feasible knowledge\ntransfer. However, such an assumption is no longer valid in a more realistic\nscenario that requires adaptation from a larger and more diverse source domain\nto a smaller target domain with less number of classes. This paper extends the\nadversarial nets-based domain adaptation and proposes a novel adversarial\nnets-based partial domain adaptation method to identify the source samples that\nare potentially from the outlier classes and, at the same time, reduce the\nshift of shared classes between domains.","url_abs":"http://arxiv.org/abs/1803.09210v2","url_pdf":"http://arxiv.org/pdf/1803.09210v2.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":"importance-weighted-adversarial-nets-for","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"partial-domain-adaptation","task_name":"Partial Domain Adaptation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.09210","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}