{"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/mind-the-class-weight-bias-weighted-maximum","title":"Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation","arxiv_id":"1705.00609","date":"2017-05-01","proceeding":"CVPR 2017 7","authors":["Hongliang Yan","Yukang Ding","Peihua Li","Qilong Wang","Yong Xu","WangMeng Zuo"],"abstract":"In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted\nas a discrepancy metric between the distributions of source and target domains.\nHowever, existing MMD-based domain adaptation methods generally ignore the\nchanges of class prior distributions, i.e., class weight bias across domains.\nThis remains an open problem but ubiquitous for domain adaptation, which can be\ncaused by changes in sample selection criteria and application scenarios. We\nshow that MMD cannot account for class weight bias and results in degraded\ndomain adaptation performance. To address this issue, a weighted MMD model is\nproposed in this paper. Specifically, we introduce class-specific auxiliary\nweights into the original MMD for exploiting the class prior probability on\nsource and target domains, whose challenge lies in the fact that the class\nlabel in target domain is unavailable. To account for it, our proposed weighted\nMMD model is defined by introducing an auxiliary weight for each class in the\nsource domain, and a classification EM algorithm is suggested by alternating\nbetween assigning the pseudo-labels, estimating auxiliary weights and updating\nmodel parameters. Extensive experiments demonstrate the superiority of our\nweighted MMD over conventional MMD for domain adaptation.","url_abs":"http://arxiv.org/abs/1705.00609v1","url_pdf":"http://arxiv.org/pdf/1705.00609v1.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":"mind-the-class-weight-bias-weighted-maximum","repo_url":"https://github.com/yhldhit/WMMD-Caffe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"mind-the-class-weight-bias-weighted-maximum","repo_url":"https://github.com/CtrlZ1/Domain-Adaptation-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mind-the-class-weight-bias-weighted-maximum","repo_url":"https://github.com/CtrlZ1/Domain-Adaptive-CodeBase","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.00609","atlas_url":"https://app.syntology.ai/?focus=1705.00609","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}