{"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/learning-domain-invariant-subspace-using","title":"Learning Domain-Invariant Subspace using Domain Features and Independence Maximization","arxiv_id":"1603.04535","date":"2016-03-15","proceeding":null,"authors":["Ke Yan","Lu Kou","David Zhang"],"abstract":"Domain adaptation algorithms are useful when the distributions of the\ntraining and the test data are different. In this paper, we focus on the\nproblem of instrumental variation and time-varying drift in the field of\nsensors and measurement, which can be viewed as discrete and continuous\ndistributional change in the feature space. We propose maximum independence\ndomain adaptation (MIDA) and semi-supervised MIDA (SMIDA) to address this\nproblem. Domain features are first defined to describe the background\ninformation of a sample, such as the device label and acquisition time. Then,\nMIDA learns a subspace which has maximum independence with the domain features,\nso as to reduce the inter-domain discrepancy in distributions. A feature\naugmentation strategy is also designed to project samples according to their\nbackgrounds so as to improve the adaptation. The proposed algorithms are\nflexible and fast. Their effectiveness is verified by experiments on synthetic\ndatasets and four real-world ones on sensors, measurement, and computer vision.\nThey can greatly enhance the practicability of sensor systems, as well as\nextend the application scope of existing domain adaptation algorithms by\nuniformly handling different kinds of distributional change.","url_abs":"http://arxiv.org/abs/1603.04535v2","url_pdf":"http://arxiv.org/pdf/1603.04535v2.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":"learning-domain-invariant-subspace-using","repo_url":"https://github.com/viggin/domain-adaptation-toolbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"learning-domain-invariant-subspace-using","repo_url":"https://github.com/zhangxuhuizju/TCA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.04535","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}