Domain generalization Person Re-identification on Attention-aware multi-operation strategery

TL;DR

This paper introduces an Attention-aware Multi-operation Strategery (AMS) that combines invariant operations and attention mechanisms to improve domain generalization in person re-identification, demonstrating significant performance gains across multiple datasets.

Contribution

The paper proposes a novel AMS module integrating IN, GW, and attention mechanisms to enhance domain-invariant feature extraction for DG Re-ID.

Findings

AMS improves generalization to unseen domains.

Significant accuracy improvements on three protocols with ten datasets.

AMS is a plug-and-play module compatible with existing architectures.

Abstract

Domain generalization person re-identification (DG Re-ID) aims to directly deploy a model trained on the source domain to the unseen target domain with good generalization, which is a challenging problem and has practical value in a real-world deployment. In the existing DG Re-ID methods, invariant operations are effective in extracting domain generalization features, and Instance Normalization (IN) or Batch Normalization (BN) is used to alleviate the bias to unseen domains. Due to domain-specific information being used to capture discriminability of the individual source domain, the generalized ability for unseen domains is unsatisfactory. To address this problem, an Attention-aware Multi-operation Strategery (AMS) for DG Re-ID is proposed to extract more generalized features. We investigate invariant operations and construct a multi-operation module based on IN and group whitening (GW) to extract domain-invariant feature representations. Furthermore, we analyze different domain-invariant characteristics, and apply spatial attention to the IN operation and channel attention to the GW operation to enhance the domain-invariant features. The proposed AMS module can be used as a plug-and-play module to incorporate into existing network architectures. Extensive experimental results show that AMS can effectively enhance the model's generalization ability to unseen domains and significantly improves the recognition performance in DG Re-ID on three protocols with ten datasets.