{"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/hard-aware-instance-adaptive-self-training","title":"Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation","arxiv_id":"2302.06992","date":"2023-02-14","proceeding":null,"authors":["Chuang Zhu","Kebin Liu","Wenqi Tang","Ke Mei","Jiaqi Zou","Tiejun Huang"],"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 problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing the scalability and performance. In this paper, we propose a hard-aware instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality and diversity of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. We further enrich the hard class pseudo-labels with inter-image information through a skillfully designed hard-aware pseudo-label augmentation. Besides, we propose the region-adaptive regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. For the non-pseudo-label region, consistency constraint is also constructed to introduce stronger supervision signals during model optimization. Our method is so concise and efficient that it is easy to be generalized to other UDA methods. Experiments on GTA5 to Cityscapes, SYNTHIA to Cityscapes, and Cityscapes to Oxford RobotCar demonstrate the superior performance of our approach compared with the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2302.06992v1","url_pdf":"https://arxiv.org/pdf/2302.06992v1.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":"hard-aware-instance-adaptive-self-training","repo_url":"https://github.com/bupt-ai-cz/hiast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"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"},{"task_slug":null,"task_name":"Unsupervised Domain Adaptation,Synthetic-to-Real Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","task":"Domain Adaptation","dataset":"GTA5 to Cityscapes","model":"Sepico + HIAST","rank_in_archive_order":12,"of":28,"metrics":{"mIoU":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","task":"Domain Adaptation","dataset":"GTA5 to Cityscapes","model":"AdaptSeg + HIAST","rank_in_archive_order":23,"of":28,"metrics":{"mIoU":"56.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"Sepico + HIAST","rank_in_archive_order":12,"of":73,"metrics":{"mIoU":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"AdaptSeg + HIAST","rank_in_archive_order":27,"of":73,"metrics":{"mIoU":"56.3"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"Sepico + HIAST","rank_in_archive_order":10,"of":38,"metrics":{"MIoU (13 classes)":"68.1","MIoU (16 classes)":"59.6"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"AdaptSeg + HIAST","rank_in_archive_order":18,"of":38,"metrics":{"MIoU (13 classes)":"60.3","MIoU (16 classes)":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"Sepico + HIAST","rank_in_archive_order":9,"of":23,"metrics":{"MIoU (16 classes)":"59.6","mIoU (13 classes)":"68.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"AdaptSeg + HIAST","rank_in_archive_order":15,"of":23,"metrics":{"MIoU (16 classes)":"53.5","mIoU (13 classes)":"60.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.06992","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}