{"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/spherereid-deep-hypersphere-manifold","title":"SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification","arxiv_id":"1807.00537","date":"2018-07-02","proceeding":null,"authors":["Xing Fan","Wei Jiang","Hao Luo","Mengjuan Fei"],"abstract":"Many current successful Person Re-Identification(ReID) methods train a model\nwith the softmax loss function to classify images of different persons and\nobtain the feature vectors at the same time. However, the underlying feature\nembedding space is ignored. In this paper, we use a modified softmax function,\ntermed Sphere Softmax, to solve the classification problem and learn a\nhypersphere manifold embedding simultaneously. A balanced sampling strategy is\nalso introduced. Finally, we propose a convolutional neural network called\nSphereReID adopting Sphere Softmax and training a single model end-to-end with\na new warming-up learning rate schedule on four challenging datasets including\nMarket-1501, DukeMTMC-reID, CHHK-03, and CUHK-SYSU. Experimental results\ndemonstrate that this single model outperforms the state-of-the-art methods on\nall four datasets without fine-tuning or re-ranking. For example, it achieves\n94.4% rank-1 accuracy on Market-1501 and 83.9% rank-1 accuracy on\nDukeMTMC-reID. The code and trained weights of our model will be released.","url_abs":"http://arxiv.org/abs/1807.00537v1","url_pdf":"http://arxiv.org/pdf/1807.00537v1.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":"spherereid-deep-hypersphere-manifold","repo_url":"https://github.com/CoinCheung/SphereReID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"spherereid-deep-hypersphere-manifold","repo_url":"https://github.com/layumi/Person_reID_baseline_pytorch","is_official":0,"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":"re-ranking","task_name":"Re-Ranking"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.00537","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}