Tri-Invariance Contrastive Framework for Robust Unsupervised Person Re-Identification

Lei Wang, Chengang Liu, Xiaoxiao Wang, Weidong Gao (), Xuejian Ge and Shunjie Zhu
Additional contact information
Lei Wang: School of Automation, Wuxi University, Wuxi 214105, China
Chengang Liu: School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China
Xiaoxiao Wang: School of Automation, Nanjing University of Information Science and Technology, Wuxi 210044, China
Weidong Gao: School of Electronic Information Engineering, Wuxi University, Wuxi 214105, China
Xuejian Ge: School of Automation, Wuxi University, Wuxi 214105, China
Shunjie Zhu: School of Automation, Nanjing University of Information Science and Technology, Wuxi 210044, China

Mathematics, 2025, vol. 13, issue 21, 1-20

Abstract: Unsupervised person re-identification (Re-ID) has been proven very effective and it boosts the performance in learning representations from unlabeled data in the dataset. Most current methods have good accuracy, but there are two main problems. First, clustering often generates noisy labels. Second, features can change because of different camera styles. Noisy labels causes incorrect optimization, which reduces the accuracy of the model. The latter results in inaccurate prediction for samples within the same category that have been captured by different cameras. Despite the significant variations inherent in the vast source data, the principles of invariance and symmetry remain crucial for effective feature recognition. In this paper, we propose a method called Invariance Constraint Contrast Learning (ICCL) to address these two problems. Specifically, we introduce center invariance and instance invariance to reduce the effect of noisy samples. We also use camera invariance to handle feature changes caused by different cameras. Center invariance and instance invariance help decrease the impact of noise. Camera invariance improves the classification accuracy by using a camera-aware classification strategy. We test our method on three common large-scale Re-ID datasets. It clearly improves the accuracy of unsupervised person Re-ID. Specifically, our approach demonstrates its effectiveness by improving mAP by 3.5% on Market-1501, 1.3% on MSMT17 and 3.5% on CUHK03 over state-of-the-art methods.

Keywords: person reidentification; contrastive learning; unsupervised learning; robust modeling (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/21/3570/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/21/3570/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:21:p:3570-:d:1789332

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().