Domain Adaptive Attention Learning for Unsupervised Person Re-Identification

TL;DR

This paper introduces a domain adaptive attention learning method for unsupervised person re-identification, effectively transferring discriminative features across datasets despite domain differences and lack of annotations.

Contribution

It proposes a novel domain adaptive attention model that separates shared and domain-specific features, improving cross-dataset transferability in unsupervised person Re-ID.

Findings

Outperforms state-of-the-art on Market-1501, DukeMTMC-reID, MSMT17.

Effectively separates domain-shared and domain-specific features.

Utilizes pseudo labels to leverage unlabeled target data.

Abstract

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper proposes a domain adaptive attention learning approach to reliably transfer discriminative representation from the labeled source domain to the unlabeled target domain. In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part. In this manner, the domain-shared part is used to capture transferable cues that can compensate cross-dataset distinctions and give positive contributions to the target task, while the domain-specific part aims to model the noisy information to avoid the negative transfer caused by domain diversity. A soft label loss is further employed to take full use of unlabeled target data by estimating pseudo labels. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 benchmarks demonstrate the proposed approach outperforms the state-of-the-arts.