WePerson: Generalizable Re-Identification From Synthetic Data With Single Query Adaptation

He Li;Mang Ye;Kehua Su;Bo Du
{"title":"WePerson: Generalizable Re-Identification From Synthetic Data With Single Query Adaptation","authors":"He Li;Mang Ye;Kehua Su;Bo Du","doi":"10.1109/TBIOM.2025.3540919","DOIUrl":null,"url":null,"abstract":"Person re-identification (ReID) aims to retrieve a target person across non-overlapping cameras. Due to the uncontrollable environment and the privacy concerns, the diversity and scale of real-world training data are usually limited, resulting in poor testing generalizability. To overcome these problems, we introduce a large-scale Weather Person dataset that generates synthetic images with different weather conditions, complex scenes, natural lighting changes, and various pedestrian accessories in a simulated camera network. The environment is fully controllable, supporting factor-by-factor analysis. To narrow the gap between synthetic data and real-world scenarios, this paper introduces a simple yet efficient domain generalization method via Single Query Adaptation (SQA), calibrating the statistics and transformation parameters in BatchNorm layers with only a single query image in the target domain. This significantly improves performance through a single adaptation epoch, greatly boosting the applicability of the ReID technique for intelligent surveillance systems. Abundant experiment results demonstrate that the WePerson dataset achieves superior performance under direct transfer setting without any real-world data training. In addition, the proposed SQA method shows amazing robustness in real-to-real, synthetic-to-real ReID, and various corruption settings. Dataset and code are available at <uri>https://github.com/lihe404/WePerson</uri>.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"7 3","pages":"458-470"},"PeriodicalIF":0.0000,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on biometrics, behavior, and identity science","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10879593/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Person re-identification (ReID) aims to retrieve a target person across non-overlapping cameras. Due to the uncontrollable environment and the privacy concerns, the diversity and scale of real-world training data are usually limited, resulting in poor testing generalizability. To overcome these problems, we introduce a large-scale Weather Person dataset that generates synthetic images with different weather conditions, complex scenes, natural lighting changes, and various pedestrian accessories in a simulated camera network. The environment is fully controllable, supporting factor-by-factor analysis. To narrow the gap between synthetic data and real-world scenarios, this paper introduces a simple yet efficient domain generalization method via Single Query Adaptation (SQA), calibrating the statistics and transformation parameters in BatchNorm layers with only a single query image in the target domain. This significantly improves performance through a single adaptation epoch, greatly boosting the applicability of the ReID technique for intelligent surveillance systems. Abundant experiment results demonstrate that the WePerson dataset achieves superior performance under direct transfer setting without any real-world data training. In addition, the proposed SQA method shows amazing robustness in real-to-real, synthetic-to-real ReID, and various corruption settings. Dataset and code are available at https://github.com/lihe404/WePerson.
WePerson:基于单查询自适应的合成数据的可泛化再识别
人物再识别(ReID)的目的是在不重叠的摄像机之间检索目标人物。由于环境的不可控和隐私问题,现实训练数据的多样性和规模往往受到限制,导致测试的泛化性较差。为了克服这些问题,我们引入了一个大规模的天气人数据集,该数据集在模拟摄像机网络中生成具有不同天气条件、复杂场景、自然光线变化和各种行人配件的合成图像。环境是完全可控的,支持逐因素分析。为了缩小合成数据与真实场景之间的差距,本文引入了一种简单而高效的领域泛化方法,即通过单查询自适应(Single Query Adaptation, SQA),在目标域中仅使用单个查询图像来校准BatchNorm层中的统计和转换参数。这大大提高了性能,通过一个单一的适应时代,极大地提高了ReID技术在智能监控系统中的适用性。大量的实验结果表明,WePerson数据集在没有任何真实数据训练的情况下,在直接传输设置下取得了优异的性能。此外,所提出的SQA方法在real-to-real、synthetic-to-real ReID和各种损坏设置中显示出惊人的鲁棒性。数据集和代码可在https://github.com/lihe404/WePerson上获得。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
10.90
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信