EANet: Enhancing Alignment for Cross-Domain Person Re-identification

TL;DR

This paper introduces EANet, a novel approach for cross-domain person re-identification that improves model generalization and adaptation through part alignment techniques, achieving state-of-the-art results across multiple datasets.

Contribution

The paper proposes Part Aligned Pooling and a Part Segmentation constraint to enhance alignment, generalization, and domain adaptation in person ReID models.

Findings

Significant improvement in cross-domain testing performance.

Effective domain adaptation using unlabeled target images.

State-of-the-art results on multiple large datasets.

Abstract

Person re-identification (ReID) has achieved significant improvement under the single-domain setting. However, directly exploiting a model to new domains is always faced with huge performance drop, and adapting the model to new domains without target-domain identity labels is still challenging. In this paper, we address cross-domain ReID and make contributions for both model generalization and adaptation. First, we propose Part Aligned Pooling (PAP) that brings significant improvement for cross-domain testing. Second, we design a Part Segmentation (PS) constraint over ReID feature to enhance alignment and improve model generalization. Finally, we show that applying our PS constraint to unlabeled target domain images serves as effective domain adaptation. We conduct extensive experiments between three large datasets, Market1501, CUHK03 and DukeMTMC-reID. Our model achieves state-of-the-art performance under both source-domain and cross-domain settings. For completeness, we also demonstrate the complementarity of our model to existing domain adaptation methods. The code is available at https://github.com/huanghoujing/EANet.