Rectifying Pseudo Label By Mutual Disagreement Learning For Unsupervised Domain Adaptation Person Re-Identification
Xu Xu, Liyan Zhang · 2021
Unsupervised domain adaptation person re-identification(re-ID) aims to transfer knowledge from the labeled source domain to unlabeled target domain, which is still a challenging task due to the large domain discrepancy. The clustering-based methods maintain advanced performance, generating pseudo-labels for unlabeled target domain images by clustering. However, not making full use of all valuable images and label noise derived from imperfect clustering results dramatically impact further performance improvement. To alleviate the above two problems, we propose a novel mutual disagreement learning(MDL) framework. We attach some of outliers(unclustered samples) with small loss to training process in an adversarial strategy manner. To rectify label noise, we train two networks and their momentum-based moving average models, making them teach each other and using prediction disagreement samples to update networks. Extensive experiments on four unsupervised domain tasks, Market-to-Duke, Duke-to-Market, Market-to-MSMT and Duke-to-MSMT, show that the advantages of our proposed MDL framework compared with other state-of-the-art methods.