Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID
IEEE Transactions on Circuits and Systems for Video Technology · 2026-09 · 36 (9) · 12828-12841
DOI: 10.1109/tcsvt.2026.3700883 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-09. Verfasst von Xulin Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In cloth-changing person re-identification (CC-ReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clothing changes. However, a spurious correlation currently limits existing ReID methods from effectively extracting these clothing-invariant features. This spurious correlation arises from clothing ownership: clothing is rarely shared across different identities, so models tend to memorize clothing cues for identity recognition, and this strategy generalizes poorly to unseen clothing. In this paper, we propose Causal Clothes-Invariant Learning (CCIL), which explicitly shifts CC-ReID from likelihood learning $P(Y|X)$ to causal intervention learning $P(Y|do(X))$ to block the clothing shortcut. CCIL realizes this intervention through three modules: a Confounder Dictionary, an Intervention Module, and Disentangle Regularization. The causality-based modeling makes the entire model naturally clothes-invariant, effectively preventing the capture of spurious correlations in feature learning. Extensive experiments validate the effectiveness of CCIL. On PRCC and DeepChange datasets, CCIL achieves Rank-1 accuracies of 66.4% and 59.2%, outperforming state-of-the-art methods by 1.4 and 4.1 percentage points, respectively.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, X., Lu, Y., Liu, B., Li, J., Liu, Y., Chu, Q., Ye, M., Ouyang, W., & Yu, N. (2026). Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID. IEEE Transactions on Circuits and Systems for Video Technology, 36(9), 12828-12841. https://doi.org/10.1109/tcsvt.2026.3700883
Vancouver
Li X, Lu Y, Liu B, Li J, Liu Y, Chu Q, et al. Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(9):12828-12841. doi:10.1109/tcsvt.2026.3700883
BibTeX
@article{Li2026,
author = {Li, Xulin and Lu, Yan and Liu, Bin and Li, Jiaze and Liu, Yating and Chu, Qi and Ye, Mang and Ouyang, Wanli and Yu, Nenghai},
title = {Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {9},
pages = {12828--12841},
doi = {10.1109/tcsvt.2026.3700883}
}
EUVIMED