{"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/drop-to-adapt-learning-discriminative","title":"Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation","arxiv_id":"1910.05562","date":"2019-10-12","proceeding":"ICCV 2019 10","authors":["Seungmin Lee","Dongwan Kim","Namil Kim","Seong-Gyun Jeong"],"abstract":"Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render suboptimal performances since they attempt to match the distributions among the domains without considering the task at hand. We propose Drop to Adapt (DTA), which leverages adversarial dropout to learn strongly discriminative features by enforcing the cluster assumption. Accordingly, we design objective functions to support robust domain adaptation. We demonstrate efficacy of the proposed method on various experiments and achieve consistent improvements in both image classification and semantic segmentation tasks. Our source code is available at https://github.com/postBG/DTA.pytorch.","url_abs":"https://arxiv.org/abs/1910.05562v1","url_pdf":"https://arxiv.org/pdf/1910.05562v1.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":"drop-to-adapt-learning-discriminative","repo_url":"https://github.com/postBG/DTA.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-visda2017","task":"Domain Adaptation","dataset":"VisDA2017","model":"DTA","rank_in_archive_order":20,"of":28,"metrics":{"Accuracy":"81.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.05562","atlas_url":"https://app.syntology.ai/?focus=1910.05562","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}