{"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/spectral-feature-transformation-for-person-re","title":"Spectral Feature Transformation for Person Re-identification","arxiv_id":"1811.11405","date":"2018-11-28","proceeding":"ICCV 2019 10","authors":["Chuanchen Luo","Yuntao Chen","Naiyan Wang","Zhao-Xiang Zhang"],"abstract":"With the surge of deep learning techniques, the field of person\nre-identification has witnessed rapid progress in recent years. Deep learning\nbased methods focus on learning a feature space where samples are clustered\ncompactly according to their corresponding identities. Most existing methods\nrely on powerful CNNs to transform the samples individually. In contrast, we\npropose to consider the sample relations in the transformation. To achieve this\ngoal, we incorporate spectral clustering technique into CNN. We derive a novel\nmodule named Spectral Feature Transformation and seamlessly integrate it into\nexisting CNN pipeline with negligible cost,which makes our method enjoy the\nbest of two worlds. Empirical studies show that the proposed approach\noutperforms previous state-of-the-art methods on four public benchmarks by a\nconsiderable margin without bells and whistles.","url_abs":"http://arxiv.org/abs/1811.11405v1","url_pdf":"http://arxiv.org/pdf/1811.11405v1.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":"spectral-feature-transformation-for-person-re","repo_url":"https://github.com/LuckyDC/SFT_REID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"spectral-feature-transformation-for-person-re","repo_url":"https://github.com/xuxu116/pytorch-reid-lite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[{"method_slug":"spectral-clustering","method_name":"Spectral Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.11405","atlas_url":"https://app.syntology.ai/?focus=1811.11405","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}