{"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/instance-adaptive-self-training-for","title":"Instance Adaptive Self-Training for Unsupervised Domain Adaptation","arxiv_id":"2008.12197","date":"2020-08-27","proceeding":"ECCV 2020 8","authors":["Ke Mei","Chuang Zhu","Jiaqi Zou","Shanghang Zhang"],"abstract":"The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing scalability and performance. In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. Besides, we propose the region-guided regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. Our method is so concise and efficient that it is easy to be generalized to other unsupervised domain adaptation methods. Experiments on 'GTA5 to Cityscapes' and 'SYNTHIA to Cityscapes' demonstrate the superior performance of our approach compared with the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2008.12197v1","url_pdf":"https://arxiv.org/pdf/2008.12197v1.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":"instance-adaptive-self-training-for","repo_url":"https://github.com/bupt-ai-cz/IAST-ECCV2020","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"instance-adaptive-self-training-for","repo_url":"https://github.com/Raykoooo/IAST","is_official":0,"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-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes","task":"Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"IAST (ResNet-101)","rank_in_archive_order":20,"of":33,"metrics":{"mIoU":"49.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"IAST(ResNet-101)","rank_in_archive_order":13,"of":28,"metrics":{"mIoU (13 classes)":"57.0"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"IAST","rank_in_archive_order":42,"of":73,"metrics":{"mIoU":"51.5"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"IAST(ResNet-101)","rank_in_archive_order":23,"of":38,"metrics":{"MIoU (13 classes)":"57.0","MIoU (16 classes)":"49.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.12197","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}