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

TL;DR

This paper introduces a multiple co-teaching framework with a mean-teaching mechanism to improve pseudo label quality in unsupervised cross-domain person re-identification, addressing self-discrepancy and network complementarity issues.

Contribution

It proposes a novel multiple co-teaching approach with mean-teaching to enhance pseudo label accuracy and exploit self-discrepancy in unsupervised domain adaptation for person re-ID.

Findings

Achieves competitive performance on large-scale datasets.

Effectively handles noisy pseudo labels in domain adaptation.

Demonstrates the benefit of self-discrepancy consideration in co-teaching.

Abstract

Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potential limitation of these clustering-based methods is that they always tend to introduce noisy labels, which will undoubtedly hamper the performance of our re-ID system. To handle this limitation, an intuitive solution is to utilize collaborative training to purify the pseudo label quality. However, there exists a challenge that the complementarity of two networks, which inevitably share a high similarity, becomes weakened gradually as training process goes on; worse still, these approaches typically ignore to consider the self-discrepancy of intra-class relations. To address this issue, in this paper, we propose a multiple co-teaching framework for domain adaptive person re-ID, opening up a promising direction about self-discrepancy problem under unsupervised condition. On top of that, a mean-teaching mechanism is leveraged to enlarge the difference and discover more complementary features. Comprehensive experiments conducted on several large-scale datasets show that our method achieves competitive performance compared with the state-of-the-arts.