English

Domain-Class Correlation Decomposition for Generalizable Person Re-Identification

Computer Vision and Pattern Recognition 2021-06-30 v1

Abstract

Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to generalize well to unseen target domains. Domain adversarial learning is a promising domain generalization method that aims to remove domain information in the latent representation through adversarial training. However, in person re-identification, the domain and class are correlated, and we theoretically show that domain adversarial learning will lose certain information about class due to this domain-class correlation. Inspired by casual inference, we propose to perform interventions to the domain factor dd, aiming to decompose the domain-class correlation. To achieve this goal, we proposed estimating the resulting representation zz^{*} caused by the intervention through first- and second-order statistical characteristic matching. Specifically, we build a memory bank to restore the statistical characteristics of each domain. Then, we use the newly generated samples {z,y,d}\{z^{*},y,d^{*}\} to compute the loss function. These samples are domain-class correlation decomposed; thus, we can learn a domain-invariant representation that can capture more class-related features. Extensive experiments show that our model outperforms the state-of-the-art methods on the large-scale domain generalization Re-ID benchmark.

Keywords

Cite

@article{arxiv.2106.15206,
  title  = {Domain-Class Correlation Decomposition for Generalizable Person Re-Identification},
  author = {Kaiwen Yang and Xinmei Tian},
  journal= {arXiv preprint arXiv:2106.15206},
  year   = {2021}
}

Comments

10 pages, 5 figures

R2 v1 2026-06-24T03:42:22.752Z