English

Learning Invariance from Generated Variance for Unsupervised Person Re-identification

Computer Vision and Pattern Recognition 2023-01-03 v1

Abstract

This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image. However, traditional data augmentation may bring to the fore undesirable distortions on identity features, which is not always favorable in id-sensitive ReID tasks. In this paper, we propose to replace traditional data augmentation with a generative adversarial network (GAN) that is targeted to generate augmented views for contrastive learning. A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. Deviating from previous GAN-based ReID methods that only work in id-unrelated space (pose and camera style), we conduct GAN-based augmentation on both id-unrelated and id-related features. We further propose specific contrastive losses to help our network learn invariance from id-unrelated and id-related augmentations. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks.

Keywords

Cite

@article{arxiv.2301.00725,
  title  = {Learning Invariance from Generated Variance for Unsupervised Person Re-identification},
  author = {Hao Chen and Yaohui Wang and Benoit Lagadec and Antitza Dantcheva and Francois Bremond},
  journal= {arXiv preprint arXiv:2301.00725},
  year   = {2023}
}

Comments

Extension of conference paper arXiv:2012.09071. Accepted to TPAMI. Project page: https://github.com/chenhao2345/GCL-extended

R2 v1 2026-06-28T07:59:44.191Z