Self-Label Refining for Unsupervised Person Re-Identification

Fully unsupervised person Re-ID is a challenging task. State-of-the-art methods perform model training with the pseudo labels generated by clustering algorithms on the unlabeled dataset. However, the label noise caused by clustering limits the performance of person Re-ID tasks. To alleviate the problem, this paper proposes a Self-Label Refining Network (SLRNet). It is considered that the local parts naturally mitigate the variation of intra-identity samples caused by cross-view. Thus, the Self-Label Refining (SLR) module estimates the similarities between global and local pseudo labels with clustering consensus, and then it refines the global pseudo labels by integrating propagated local pseudo labels into global pseudo labels. Meanwhile, a symmetric ClusterNCE loss is further proposed to enhance the robustness of the network to noisy labels. Extensive experiments show that our method achieves state-of-the-art performance on three widely used person Re-ID datasets.