{"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/ccup-a-controllable-synthetic-data-generation","title":"CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Models","arxiv_id":"2410.13567","date":"2024-10-17","proceeding":null,"authors":["Yujian Zhao","Chengru Wu","Yinong Xu","Xuanzheng Du","Ruiyu Li","Guanglin Niu"],"abstract":"Cloth-changing person re-identification (CC-ReID), also known as Long-Term Person Re-Identification (LT-ReID) is a critical and challenging research topic in computer vision that has recently garnered significant attention. However, due to the high cost of constructing CC-ReID data, the existing data-driven models are hard to train efficiently on limited data, causing overfitting issue. To address this challenge, we propose a low-cost and efficient pipeline for generating controllable and high-quality synthetic data simulating the surveillance of real scenarios specific to the CC-ReID task. Particularly, we construct a new self-annotated CC-ReID dataset named Cloth-Changing Unreal Person (CCUP), containing 6,000 IDs, 1,179,976 images, 100 cameras, and 26.5 outfits per individual. Based on this large-scale dataset, we introduce an effective and scalable pretrain-finetune framework for enhancing the generalization capabilities of the traditional CC-ReID models. The extensive experiments demonstrate that two typical models namely TransReID and FIRe^2, when integrated into our framework, outperform other state-of-the-art models after pretraining on CCUP and finetuning on the benchmarks such as PRCC, VC-Clothes and NKUP. The CCUP is available at: https://github.com/yjzhao1019/CCUP.","url_abs":"https://arxiv.org/abs/2410.13567v3","url_pdf":"https://arxiv.org/pdf/2410.13567v3.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":"ccup-a-controllable-synthetic-data-generation","repo_url":"https://github.com/yjzhao1019/ccup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"cloth-changing-person-re-identification","task_name":"Cloth-Changing Person Re-Identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"}],"methods":[],"datasets_introduced":[{"slug":"ccup","name":"CCUP","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-prcc","task":"Person Re-Identification","dataset":"PRCC","model":"TransReid+CCUP","rank_in_archive_order":9,"of":13,"metrics":{" Rank-1":"58.9","mAP":"59.0"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-vc-clothes","task":"Person Re-Identification","dataset":"VC-Clothes","model":"Transreid+CCUP","rank_in_archive_order":3,"of":6,"metrics":{" Rank-1":"83.3","mAP":"83.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}