{"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/sliced-wasserstein-discrepancy-for","title":"Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation","arxiv_id":"1903.04064","date":"2019-03-10","proceeding":"CVPR 2019 6","authors":["Chen-Yu Lee","Tanmay Batra","Mohammad Haris Baig","Daniel Ulbricht"],"abstract":"In this work, we connect two distinct concepts for unsupervised domain\nadaptation: feature distribution alignment between domains by utilizing the\ntask-specific decision boundary and the Wasserstein metric. Our proposed sliced\nWasserstein discrepancy (SWD) is designed to capture the natural notion of\ndissimilarity between the outputs of task-specific classifiers. It provides a\ngeometrically meaningful guidance to detect target samples that are far from\nthe support of the source and enables efficient distribution alignment in an\nend-to-end trainable fashion. In the experiments, we validate the effectiveness\nand genericness of our method on digit and sign recognition, image\nclassification, semantic segmentation, and object detection.","url_abs":"http://arxiv.org/abs/1903.04064v1","url_pdf":"http://arxiv.org/pdf/1903.04064v1.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":"sliced-wasserstein-discrepancy-for","repo_url":"https://github.com/apple/ml-cvpr2019-swd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"sliced-wasserstein-discrepancy-for","repo_url":"https://github.com/kevinmusgrave/pytorch-adapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-visda2017","task":"Domain Adaptation","dataset":"VisDA2017","model":"SWD","rank_in_archive_order":24,"of":28,"metrics":{"Accuracy":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"SWD","rank_in_archive_order":19,"of":28,"metrics":{"mIoU (13 classes)":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"SWD","rank_in_archive_order":61,"of":73,"metrics":{"mIoU":"44.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.04064","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}