English

Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification

Computer Vision and Pattern Recognition 2023-05-11 v1

Abstract

Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID). It can provide discriminative identity features and eliminate the negative effects caused by the confounder--clothing changes. But we argue that there exists a strong spurious correlation between clothes and human identity, that restricts the common likelihood-based ReID method P(Y|X) to extract clothes-irrelevant features. In this paper, we propose a new Causal Clothes-Invariant Learning (CCIL) method to achieve clothes-invariant feature learning by modeling causal intervention P(Y|do(X)). This new causality-based model is inherently invariant to the confounder in the causal view, which can achieve the clothes-invariant features and avoid the barrier faced by the likelihood-based methods. Extensive experiments on three CC-ReID benchmarks, including PRCC, LTCC, and VC-Clothes, demonstrate the effectiveness of our approach, which achieves a new state of the art.

Keywords

Cite

@article{arxiv.2305.06145,
  title  = {Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification},
  author = {Xulin Li and Yan Lu and Bin Liu and Yuenan Hou and Yating Liu and Qi Chu and Wanli Ouyang and Nenghai Yu},
  journal= {arXiv preprint arXiv:2305.06145},
  year   = {2023}
}
R2 v1 2026-06-28T10:31:03.589Z