{"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/selective-partial-domain-adaptation","title":"Selective Partial Domain Adaptation","arxiv_id":null,"date":"2022-10-01","proceeding":"British Machine Vision Conference 2022 10","authors":["Pengxin Guo","Jinjing Zhu","Yu Zhang"],"abstract":"Partial Domain Adaptation (PDA), which assumes that the label space of the target domain is a subset of that in the source domain, has attracted much attention in recent years. Due to the difference in the label space of these two domains, it is hard to directly\r\nalign these two domains in PDA. To solve this problem, we propose a Selective Partial Domain Adaptation (SPDA) method, which selects useful data for the adaptation to the target domain. Specifically, we firstly design a Maximum of Cosine (MoC) similarity\r\nfunction customized for PDA to select useful data in the source domain to decrease the domain discrepancy. In the MoC similarity function, for each target sample, we select the source sample with the maximal cosine similarity for adaptation. Moreover, a selective training method is designed to add useful target data into the source domain. In detail, the selective training method firstly assigns pseudo-labels to target samples with the selftraining strategy and then adds target samples with high confidence in terms of pseudolabels to the source domain. Based on these two selection operations, the proposed SPDA method can select useful data for domain adaptation. Experiments on several datasets\r\ndemonstrate the effectiveness of the proposed SPDA method.","url_abs":"https://bmvc2022.mpi-inf.mpg.de/0420.pdf","url_pdf":"https://bmvc2022.mpi-inf.mpg.de/0420.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":"selective-partial-domain-adaptation","repo_url":"https://github.com/Pengxin-Guo/SPDA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"selective-partial-domain-adaptation","repo_url":"https://github.com/gpx333/spda","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"partial-domain-adaptation","task_name":"Partial Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/partial-domain-adaptation-on-office-31","task":"Partial Domain Adaptation","dataset":"Office-31","model":"SPDA","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy (%)":"98.01"},"uses_additional_data":false},{"leaderboard":"/sota/partial-domain-adaptation-on-office-home","task":"Partial Domain Adaptation","dataset":"Office-Home","model":"SPDA","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy (%)":"77.12"},"uses_additional_data":false},{"leaderboard":"/sota/partial-domain-adaptation-on-visda2017","task":"Partial Domain Adaptation","dataset":"VisDA2017","model":"SPDA","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy (%)":"87.69"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}