Cooperative Refinement Learning for domain adaptive person Re-identification

Domain adaptive person re-identification (re-ID) targets at identifying the same persons' images in unlabeled target domain. Some existing domain adaptive Person re-ID methods assigned pseudo labels by clustering algorithms on the target domain, which tends to generate noisy labels and neglect samples with low confidence as outliers. These may hinder the retraining process, thereby limiting the model's generalization ability. In order to overcome these problems, we propose a Cooperative Refinement Learning (CooRL) framework, which resists noisy labels and takes advantage of the outliers by developing a multi-branches structure with refinement mechanism. Specifically, a mean attention guided network is leveraged to learn more complementary features from pure and noisy samples generated by clustering, which includes a mean network and two sub-branches. Meanwhile, to better optimize the neural networks, CooRL jointly refines and aligns the pseudo labels of subbranches by progressively adjusting the predicted logits through the mean network. Comprehensive experimental results have demonstrated that our proposed method can achieve excellent performances on benchmark datasets. (C) 2022 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a Cooperative Refinement Learning (CooRL) framework to address the issues of noisy labels and outlier samples in domain adaptive person re-identification. By developing a multi-branches structure and refinement mechanism, this method can learn more complementary features from pure and noisy samples and optimize the neural network by progressively adjusting the pseudo labels.