{"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/dual-level-interaction-for-domain-adaptive","title":"Dual-level Interaction for Domain Adaptive Semantic Segmentation","arxiv_id":"2307.07972","date":"2023-07-16","proceeding":null,"authors":["Dongyu Yao","Boheng Li"],"abstract":"Self-training approach recently secures its position in domain adaptive semantic segmentation, where a model is trained with target domain pseudo-labels. Current advances have mitigated noisy pseudo-labels resulting from the domain gap. However, they still struggle with erroneous pseudo-labels near the boundaries of the semantic classifier. In this paper, we tackle this issue by proposing a dual-level interaction for domain adaptation (DIDA) in semantic segmentation. Explicitly, we encourage the different augmented views of the same pixel to have not only similar class prediction (semantic-level) but also akin similarity relationship with respect to other pixels (instance-level). As it's impossible to keep features of all pixel instances for a dataset, we, therefore, maintain a labeled instance bank with dynamic updating strategies to selectively store the informative features of instances. Further, DIDA performs cross-level interaction with scattering and gathering techniques to regenerate more reliable pseudo-labels. Our method outperforms the state-of-the-art by a notable margin, especially on confusing and long-tailed classes. Code is available at \\href{https://github.com/RainJamesY/DIDA}","url_abs":"https://arxiv.org/abs/2307.07972v2","url_pdf":"https://arxiv.org/pdf/2307.07972v2.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":"dual-level-interaction-for-domain-adaptive","repo_url":"https://github.com/rainjamesy/dida","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":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"DIDA","rank_in_archive_order":6,"of":20,"metrics":{"mIoU":"71.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"DIDA","rank_in_archive_order":7,"of":23,"metrics":{"MIoU (16 classes)":"63.3","mIoU":"63.3","mIoU (13 classes)":"70.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}