{"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/weakly-supervised-person-re-identification","title":"Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark","arxiv_id":"1904.03845","date":"2019-04-08","proceeding":null,"authors":["Guangrun Wang","Guangcong Wang","Xujie Zhang","Jian-Huang Lai","Zhengtao Yu","Liang Lin"],"abstract":"Person re-identification (Re-ID) benefits greatly from the accurate annotations of existing datasets (e.g., CUHK03 [1] and Market-1501 [2]), which are quite expensive because each image in these datasets has to be assigned with a proper label. In this work, we ease the annotation of Re-ID by replacing the accurate annotation with inaccurate annotation, i.e., we group the images into bags in terms of time and assign a bag-level label for each bag. This greatly reduces the annotation effort and leads to the creation of a large-scale Re-ID benchmark called SYSU-30$k$. The new benchmark contains $30k$ individuals, which is about $20$ times larger than CUHK03 ($1.3k$ individuals) and Market-1501 ($1.5k$ individuals), and $30$ times larger than ImageNet ($1k$ categories). It sums up to 29,606,918 images. Learning a Re-ID model with bag-level annotation is called the weakly supervised Re-ID problem. To solve this problem, we introduce a differentiable graphical model to capture the dependencies from all images in a bag and generate a reliable pseudo label for each person image. The pseudo label is further used to supervise the learning of the Re-ID model. When compared with the fully supervised Re-ID models, our method achieves state-of-the-art performance on SYSU-30$k$ and other datasets. The code, dataset, and pretrained model will be available at \\url{https://github.com/wanggrun/SYSU-30k}.","url_abs":"https://arxiv.org/abs/1904.03845v3","url_pdf":"https://arxiv.org/pdf/1904.03845v3.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":"weakly-supervised-person-re-identification","repo_url":"https://github.com/wanggrun/SYSU-30k","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"}],"methods":[],"datasets_introduced":[{"slug":"sysu-30k","name":"SYSU-30k","full_name":null}],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-sysu-30k","task":"Person Re-Identification","dataset":"SYSU-30k","model":"DGL (weakly-supervised)","rank_in_archive_order":2,"of":10,"metrics":{" Rank-1":"26.9"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}