Style Normalization and Restitution for Generalizable Person Re-identification

Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in filtering out identity-irrelevant interference and learning domain-invariant person representations. In this paper, we aim to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains. To achieve this goal, we propose a simple yet effective Style Normalization and Restitution (SNR) module. Specifically, we filter out style variations (e.g., illumination, color contrast) by Instance Normalization (IN). However, such a process inevitably removes discriminative information. We propose to distill identity-relevant feature from the removed information and restitute it to the network to ensure high discrimination. For better disentanglement, we enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features. Extensive experiments demonstrate the strong generalization capability of our framework. Our models empowered by the SNR modules significantly outperform the state-of-the-art domain generalization approaches on multiple widely-used person ReID benchmarks, and also show superiority on unsupervised domain adaptation.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Unsupervised Domain Adaptation Duke to Market SNR mAP 61.7 # 9
rank-1 82.8 # 9
rank-5 - # 16
rank-10 - # 16
Unsupervised Domain Adaptation Market to Duke SNR mAP 58.1 # 7
rank-1 76.3 # 6
rank-5 - # 15
rank-10 - # 15

Methods