{"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/cluda-contrastive-learning-in-unsupervised","title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","arxiv_id":"2208.14227","date":"2022-08-27","proceeding":null,"authors":["Midhun Vayyat","Jaswin Kasi","Anuraag Bhattacharya","Shuaib Ahmed","Rahul Tallamraju"],"abstract":"In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network. More specifically, we extract a multi-level fused-feature map from the encoder, and apply contrastive loss across different classes and different domains, via source-target mixing of images. We consistently improve performance on various feature encoder architectures and for different domain adaptation datasets in semantic segmentation. Furthermore, we introduce a learned-weighted contrastive loss to improve upon on a state-of-the-art multi-resolution training approach in UDA. We produce state-of-the-art results on GTA $\\rightarrow$ Cityscapes (74.4 mIOU, +0.6) and Synthia $\\rightarrow$ Cityscapes (67.2 mIOU, +1.4) datasets. CLUDA effectively demonstrates contrastive learning in UDA as a generic method, which can be easily integrated into any existing UDA for semantic segmentation tasks. Please refer to the supplementary material for the details on implementation.","url_abs":"https://arxiv.org/abs/2208.14227v2","url_pdf":"https://arxiv.org/pdf/2208.14227v2.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":"cluda-contrastive-learning-in-unsupervised","repo_url":"https://github.com/user0407/CLUDA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"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":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"HRDA + CLUDA","rank_in_archive_order":4,"of":73,"metrics":{"mIoU":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"DAFormer + CLUDA","rank_in_archive_order":8,"of":73,"metrics":{"mIoU":"70.11"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":"Synthetic-to-Real Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CLUDA+HRDA","rank_in_archive_order":4,"of":38,"metrics":{"MIoU (16 classes)":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gta5-to-3","task":"Unsupervised Domain Adaptation","dataset":"GTA5-to-Cityscapes","model":"CLUDA+HRDA","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":"Unsupervised Domain Adaptation","dataset":"GTAV-to-Cityscapes Labels","model":"CLUDA+HRDA","rank_in_archive_order":3,"of":20,"metrics":{"mIoU":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-synthia-to","task":"Unsupervised Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"CLUDA+HRDA","rank_in_archive_order":22,"of":23,"metrics":{"mIoU":"67.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.14227","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}