Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification

TL;DR

This paper introduces an exemplar memory approach to enforce invariance properties in domain adaptive person re-identification, significantly improving accuracy by addressing intra-domain variations.

Contribution

It proposes a novel exemplar memory mechanism that enforces exemplar, camera, and neighborhood invariances, enhancing domain adaptation in person re-ID.

Findings

Outperforms state-of-the-art methods on three re-ID datasets.

Effectively enforces invariance properties with minimal computational overhead.

Demonstrates the importance of intra-domain invariance modeling for domain adaptation.

Abstract

This paper considers the domain adaptive person re-identification (re-ID) problem: learning a re-ID model from a labeled source domain and an unlabeled target domain. Conventional methods are mainly to reduce feature distribution gap between the source and target domains. However, these studies largely neglect the intra-domain variations in the target domain, which contain critical factors influencing the testing performance on the target domain. In this work, we comprehensively investigate into the intra-domain variations of the target domain and propose to generalize the re-ID model w.r.t three types of the underlying invariance, i.e., exemplar-invariance, camera-invariance and neighborhood-invariance. To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties. The memory allows us to enforce the invariance constraints over global training batch without significantly increasing computation cost. Experiment demonstrates that the three invariance properties and the proposed memory are indispensable towards an effective domain adaptation system. Results on three re-ID domains show that our domain adaptation accuracy outperforms the state of the art by a large margin. Code is available at: https://github.com/zhunzhong07/ECN