Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification

06/11/2020
by   Wenhao Wang, et al.
0

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 troubles 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. In this paper, we propose 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 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 of 9.4 Market-to-Duke, Duke-to-MSMT, and Market-to-MSMT UDA tasks, respectively.

READ FULL TEXT
research
01/06/2020

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Person re-identification (re-ID) aims at identifying the same persons' i...
research
08/07/2021

Towards Discriminative Representation Learning for Unsupervised Person Re-identification

In this work, we address the problem of unsupervised domain adaptation f...
research
09/20/2020

Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling

Person Re-Identification (re-ID) aims at retrieving images of the same p...
research
01/29/2023

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

Unsupervised domain adaptation person re-identification (Re-ID) aims to ...
research
12/28/2021

Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification

Clustering-based unsupervised domain adaptive (UDA) person re-identifica...
research
04/06/2021

Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification

Employing clustering strategy to assign unlabeled target images with pse...
research
06/29/2021

Domain adaptation for person re-identification on new unlabeled data using AlignedReID++

In the world where big data reigns and there is plenty of hardware prepa...

Please sign up or login with your details

Forgot password? Click here to reset