Learning Multiple Granularity Features for Unsupervised Person Re-Identification

Abstract

Local features have been shown effective in supervised person re-identification (Re-ID). However, it is hard to obtain workable local features in an unsupervised situation. In this paper, we propose a novel method to learn discriminative multiple granularity features in unsupervised domain adaptation (UDA) Re-ID. Firstly, we propose Multiple Granularity Memory Dictionary Group (MGMDG) to learn discriminative local features and global features respectively by contrastive learning for features of each granularity with the corresponding memory dictionary. Secondly, we design a teacher-student framework in which the teacher model supervises the student model to learn the multiple granularity features with a soft triplet loss. Finally, we use the concatenation of multiple granularity features to generate better pseudo labels for local features. Extensive experimental results show that the performance of the proposed method on Market1501, DukeMTMC, MSMT17 datasets significantly outperforms the state-of-the-art UDA Re-ID methods by a large margin.