{"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/self-ensembling-for-visual-domain-adaptation","title":"Self-ensembling for visual domain adaptation","arxiv_id":"1706.05208","date":"2017-06-16","proceeding":"ICLR 2018 1","authors":["Geoffrey French","Michal Mackiewicz","Mark Fisher"],"abstract":"This paper explores the use of self-ensembling for visual domain adaptation\nproblems. Our technique is derived from the mean teacher variant (Tarvainen et\nal., 2017) of temporal ensembling (Laine et al;, 2017), a technique that\nachieved state of the art results in the area of semi-supervised learning. We\nintroduce a number of modifications to their approach for challenging domain\nadaptation scenarios and evaluate its effectiveness. Our approach achieves\nstate of the art results in a variety of benchmarks, including our winning\nentry in the VISDA-2017 visual domain adaptation challenge. In small image\nbenchmarks, our algorithm not only outperforms prior art, but can also achieve\naccuracy that is close to that of a classifier trained in a supervised fashion.","url_abs":"http://arxiv.org/abs/1706.05208v4","url_pdf":"http://arxiv.org/pdf/1706.05208v4.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":"self-ensembling-for-visual-domain-adaptation","repo_url":"https://github.com/Britefury/self-ensemble-visual-domain-adapt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"self-ensembling-for-visual-domain-adaptation","repo_url":"https://github.com/domainadaptation/salad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}},{"paper_slug":"self-ensembling-for-visual-domain-adaptation","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-mnist-to-usps","task":"Domain Adaptation","dataset":"MNIST-to-USPS","model":"Mean teacher","rank_in_archive_order":4,"of":14,"metrics":{"Accuracy":"98.26"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-svhn-to-mnist","task":"Domain Adaptation","dataset":"SVHN-to-MNIST","model":"Mean teacher","rank_in_archive_order":1,"of":14,"metrics":{"Accuracy":"99.18"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synth-signs-to-gtsrb","task":"Domain Adaptation","dataset":"Synth Signs-to-GTSRB","model":"Mean teacher","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"98.66"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-usps-to-mnist","task":"Domain Adaptation","dataset":"USPS-to-MNIST","model":"Mean teacher","rank_in_archive_order":6,"of":14,"metrics":{"Accuracy":"98.07"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-visda2017","task":"Domain Adaptation","dataset":"VisDA2017","model":"Mean teacher","rank_in_archive_order":17,"of":28,"metrics":{"Accuracy":"85.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.05208","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}