{"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/joint-geometrical-and-statistical-alignment","title":"Joint Geometrical and Statistical Alignment for Visual Domain Adaptation","arxiv_id":"1705.05498","date":"2017-05-16","proceeding":"CVPR 2017 7","authors":["Jing Zhang","Wanqing Li","Philip Ogunbona"],"abstract":"This paper presents a novel unsupervised domain adaptation method for\ncross-domain visual recognition. We propose a unified framework that reduces\nthe shift between domains both statistically and geometrically, referred to as\nJoint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two\ncoupled projections that project the source domain and target domain data into\nlow dimensional subspaces where the geometrical shift and distribution shift\nare reduced simultaneously. The objective function can be solved efficiently in\na closed form. Extensive experiments have verified that the proposed method\nsignificantly outperforms several state-of-the-art domain adaptation methods on\na synthetic dataset and three different real world cross-domain visual\nrecognition tasks.","url_abs":"http://arxiv.org/abs/1705.05498v1","url_pdf":"http://arxiv.org/pdf/1705.05498v1.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":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-office-caltech","task":"Domain Adaptation","dataset":"Office-Caltech","model":"JGSA[[Zhang, Li, and Ogunbona2017]]","rank_in_archive_order":5,"of":8,"metrics":{"Average Accuracy":"90.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.05498","atlas_url":"https://app.syntology.ai/?focus=1705.05498","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}