{"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/deliberated-domain-bridging-for-domain","title":"Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation","arxiv_id":"2209.07695","date":"2022-09-16","proceeding":null,"authors":["Lin Chen","Zhixiang Wei","Xin Jin","Huaian Chen","Miao Zheng","Kai Chen","Yi Jin"],"abstract":"In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually and softly via various intermediate spaces, dubbed domain bridging (DB). However, for dense prediction tasks such as domain adaptive semantic segmentation (DASS), existing solutions have mostly relied on rough style transfer and how to elegantly bridge domains is still under-explored. In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space. At the heart of DDB lies a dual-path domain bridging step for generating two intermediate domains using the coarse-wise and the fine-wise data mixing techniques, alongside a cross-path knowledge distillation step for taking two complementary models trained on generated intermediate samples as 'teachers' to develop a superior 'student' in a multi-teacher distillation manner. These two optimization steps work in an alternating way and reinforce each other to give rise to DDB with strong adaptation power. Extensive experiments on adaptive segmentation tasks with different settings demonstrate that our DDB significantly outperforms state-of-the-art methods. Code is available at https://github.com/xiaoachen98/DDB.git.","url_abs":"https://arxiv.org/abs/2209.07695v3","url_pdf":"https://arxiv.org/pdf/2209.07695v3.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":"deliberated-domain-bridging-for-domain","repo_url":"https://github.com/xiaoachen98/DDB","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-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","task":"Domain Adaptation","dataset":"GTA5 to Cityscapes","model":"DDB","rank_in_archive_order":14,"of":28,"metrics":{"mIoU":"62.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-gtav-to-cityscapes-1","task":"Domain Adaptation","dataset":"GTAV to Cityscapes+Mapillary","model":"DDB","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"58.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-gtav-synscapes-to","task":"Domain Adaptation","dataset":"GTAV+Synscapes to Cityscapes","model":"DDB","rank_in_archive_order":1,"of":6,"metrics":{"mIoU":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-gtav-to","task":"Image-to-Image Translation","dataset":"GTAV-to-Cityscapes Labels","model":"DDB","rank_in_archive_order":10,"of":22,"metrics":{"mIoU":"62.7"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"DDB","rank_in_archive_order":14,"of":73,"metrics":{"mIoU":"62.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.07695","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}