{"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/deep-group-shuffling-random-walk-for-person","title":"Deep Group-shuffling Random Walk for Person Re-identification","arxiv_id":"1807.11178","date":"2018-07-30","proceeding":"CVPR 2018 6","authors":["Yantao Shen","Hongsheng Li","Tong Xiao","Shuai Yi","Dapeng Chen","Xiaogang Wang"],"abstract":"Person re-identification aims at finding a person of interest in an image\ngallery by comparing the probe image of this person with all the gallery\nimages. It is generally treated as a retrieval problem, where the affinities\nbetween the probe image and gallery images (P2G affinities) are used to rank\nthe retrieved gallery images. However, most existing methods only consider P2G\naffinities but ignore the affinities between all the gallery images (G2G\naffinity). Some frameworks incorporated G2G affinities into the testing\nprocess, which is not end-to-end trainable for deep neural networks. In this\npaper, we propose a novel group-shuffling random walk network for fully\nutilizing the affinity information between gallery images in both the training\nand testing processes. The proposed approach aims at end-to-end refining the\nP2G affinities based on G2G affinity information with a simple yet effective\nmatrix operation, which can be integrated into deep neural networks. Feature\ngrouping and group shuffle are also proposed to apply rich supervisions for\nlearning better person features. The proposed approach outperforms\nstate-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets by\nlarge margins, which demonstrate the effectiveness of our approach.","url_abs":"http://arxiv.org/abs/1807.11178v1","url_pdf":"http://arxiv.org/pdf/1807.11178v1.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":"deep-group-shuffling-random-walk-for-person","repo_url":"https://github.com/YantaoShen/kpm_rw_person_reid","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.11178","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}