{"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-a-discriminative-null-space-for","title":"Learning a Discriminative Null Space for Person Re-identification","arxiv_id":"1603.02139","date":"2016-03-07","proceeding":"CVPR 2016 6","authors":["Li Zhang","Tao Xiang","Shaogang Gong"],"abstract":"Most existing person re-identification (re-id) methods focus on learning the\noptimal distance metrics across camera views. Typically a person's appearance\nis represented using features of thousands of dimensions, whilst only hundreds\nof training samples are available due to the difficulties in collecting matched\ntraining images. With the number of training samples much smaller than the\nfeature dimension, the existing methods thus face the classic small sample size\n(SSS) problem and have to resort to dimensionality reduction techniques and/or\nmatrix regularisation, which lead to loss of discriminative power. In this\nwork, we propose to overcome the SSS problem in re-id distance metric learning\nby matching people in a discriminative null space of the training data. In this\nnull space, images of the same person are collapsed into a single point thus\nminimising the within-class scatter to the extreme and maximising the relative\nbetween-class separation simultaneously. Importantly, it has a fixed dimension,\na closed-form solution and is very efficient to compute. Extensive experiments\ncarried out on five person re-identification benchmarks including VIPeR,\nPRID2011, CUHK01, CUHK03 and Market1501 show that such a simple approach beats\nthe state-of-the-art alternatives, often by a big margin.","url_abs":"http://arxiv.org/abs/1603.02139v1","url_pdf":"http://arxiv.org/pdf/1603.02139v1.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":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"DNS","rank_in_archive_order":120,"of":135,"metrics":{"Rank-1":"61.02","mAP":"35.68"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}