{"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/disjoint-label-space-transfer-learning-with","title":"Disjoint Label Space Transfer Learning with Common Factorised Space","arxiv_id":"1812.02605","date":"2018-12-06","proceeding":null,"authors":["Xiaobin Chang","Yongxin Yang","Tao Xiang","Timothy M. Hospedales"],"abstract":"In this paper, a unified approach is presented to transfer learning that\naddresses several source and target domain label-space and annotation\nassumptions with a single model. It is particularly effective in handling a\nchallenging case, where source and target label-spaces are disjoint, and\noutperforms alternatives in both unsupervised and semi-supervised settings. The\nkey ingredient is a common representation termed Common Factorised Space. It is\nshared between source and target domains, and trained with an unsupervised\nfactorisation loss and a graph-based loss. With a wide range of experiments, we\ndemonstrate the flexibility, relevance and efficacy of our method, both in the\nchallenging cases with disjoint label spaces, and in the more conventional\ncases such as unsupervised domain adaptation, where the source and target\ndomains share the same label-sets.","url_abs":"http://arxiv.org/abs/1812.02605v1","url_pdf":"http://arxiv.org/pdf/1812.02605v1.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":[],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"CFSM","rank_in_archive_order":22,"of":26,"metrics":{"mAP":"28.3","rank-1":"61.2","rank-10":"-","rank-5":"-"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to","task":"Unsupervised Domain Adaptation","dataset":"Market to Duke","model":"CFSM","rank_in_archive_order":21,"of":25,"metrics":{"mAP":"27.3","rank-1":"49.8","rank-10":"-","rank-5":"-"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.02605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}