{"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/hard-aware-point-to-set-deep-metric-for","title":"Hard-Aware Point-to-Set Deep Metric for Person Re-identification","arxiv_id":"1807.11206","date":"2018-07-30","proceeding":"ECCV 2018 9","authors":["Rui Yu","Zhiyong Dou","Song Bai","Zhao-Xiang Zhang","Yongchao Xu","Xiang Bai"],"abstract":"Person re-identification (re-ID) is a highly challenging task due to large\nvariations of pose, viewpoint, illumination, and occlusion. Deep metric\nlearning provides a satisfactory solution to person re-ID by training a deep\nnetwork under supervision of metric loss, e.g., triplet loss. However, the\nperformance of deep metric learning is greatly limited by traditional sampling\nmethods. To solve this problem, we propose a Hard-Aware Point-to-Set (HAP2S)\nloss with a soft hard-mining scheme. Based on the point-to-set triplet loss\nframework, the HAP2S loss adaptively assigns greater weights to harder samples.\nSeveral advantageous properties are observed when compared with other\nstate-of-the-art loss functions: 1) Accuracy: HAP2S loss consistently achieves\nhigher re-ID accuracies than other alternatives on three large-scale benchmark\ndatasets; 2) Robustness: HAP2S loss is more robust to outliers than other\nlosses; 3) Flexibility: HAP2S loss does not rely on a specific weight function,\ni.e., different instantiations of HAP2S loss are equally effective. 4)\nGenerality: In addition to person re-ID, we apply the proposed method to\ngeneric deep metric learning benchmarks including CUB-200-2011 and Cars196, and\nalso achieve state-of-the-art results.","url_abs":"http://arxiv.org/abs/1807.11206v1","url_pdf":"http://arxiv.org/pdf/1807.11206v1.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":"hard-aware-point-to-set-deep-metric-for","repo_url":"https://github.com/PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.11206","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}