DEX: Domain Embedding Expansion for Generalized Person Re-identification

TL;DR

This paper introduces DEX, a domain embedding expansion module that enhances the generalization of person re-identification models across unseen domains without additional fine-tuning, outperforming existing methods on multiple benchmarks.

Contribution

The paper proposes DEX and DEXLite modules that dynamically augment features for better domain generalization in Person ReID, compatible with existing models and scalable to large datasets.

Findings

Significant performance improvements on unseen datasets.

Outperforms state-of-the-art DG Person ReID methods.

Compatible with multiple existing architectures.

Abstract

In recent years, supervised Person Re-identification (Person ReID) approaches have demonstrated excellent performance. However, when these methods are applied to inputs from a different camera network, they typically suffer from significant performance degradation. Different from most domain adaptation (DA) approaches addressing this issue, we focus on developing a domain generalization (DG) Person ReID model that can be deployed without additional fine-tuning or adaptation. In this paper, we propose the Domain Embedding Expansion (DEX) module. DEX dynamically manipulates and augments deep features based on person and domain labels during training, significantly improving the generalization capability and robustness of Person ReID models to unseen domains. We also developed a light version of DEX (DEXLite), applying negative sampling techniques to scale to larger datasets and reduce memory usage for multi-branch networks. Our proposed DEX and DEXLite can be combined with many existing methods, Bag-of-Tricks (BagTricks), the Multi-Granularity Network (MGN), and Part-Based Convolutional Baseline (PCB), in a plug-and-play manner. With DEX and DEXLite, existing methods can gain significant improvements when tested on other unseen datasets, thereby demonstrating the general applicability of our method. Our solution outperforms the state-of-the-art DG Person ReID methods in all large-scale benchmarks as well as in most the small-scale benchmarks.