Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and beyond

Authors

Wenhao Wang, Inception Institute of Artificial Intelligence & ReLER Lab, University of Technology Sydney
Fang Zhao, Tencent AI Lab, Shenzhen, China
Shengcai Liao, Inception Institute of Artificial Intelligence
Ling Shao, Inception Institute of Artificial Intelligence & Mohamed bin Zayed University of Artificial Intelligence

Document Type

Article

Publication Title

IEEE Transactions on Image Processing

Abstract

Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical self-training method is to use pseudo-labels generated by clustering algorithms to iteratively optimize the model on the target domain. However, a drawback to this is that noisy pseudo-labels generally cause trouble in learning. To address this problem, a mutual learning method by dual networks has been developed to produce reliable soft labels. However, as the two neural networks gradually converge, their complementarity is weakened and they likely become biased towards the same kind of noise. This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels. Specifically, we first introduce a parameter-free module, the WaveBlock, which creates a difference between features learned by two networks by waving blocks of feature maps differently. Then, an attention mechanism is leveraged to enlarge the difference created and discover more complementary features. Furthermore, two kinds of combination strategies, i.e. pre-attention and post-attention, are explored. Experiments demonstrate that the proposed method achieves state-of-the-art performance with significant improvements on multiple UDA person re-identification tasks. We also prove the generality of the proposed method by applying it to vehicle re-identification and image classification tasks. Our codes and models are available at: AWB.© 1992-2012 IEEE.

First Page

1532

Last Page

1544

DOI

10.1109/TIP.2022.3140614

Publication Date

1-11-2022

Keywords

attentive WaveBlock, Person re-identification, unsupervised domain adaptation

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

W. Wang, F. Zhao, S. Liao and L. Shao, "Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond," in IEEE Transactions on Image Processing, vol. 31, pp. 1532-1544, 2022, doi: 10.1109/TIP.2022.3140614.