Learning Invariance from Generated Variance for Unsupervised Person Re-identification

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.

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

References in corpus (5)

• Bootstrap your own latent: A new approach to self-supervised Learning
• AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• Unsupervised Person Re-identification via Multi-label Classification
• OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World

Cited by in corpus (1)

• Anti-Forgetting Adaptation for Unsupervised Person Re-identification