Rethinking Sampling Strategies for Unsupervised Person Re-identification

Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design or loss function, we show in this paper that sampling strategy plays an equally important role. We analyze the reasons for differences in performance between various sampling strategies under the same framework and loss function. We suggest that deteriorated over-fitting is an important factor causing poor performance, and enhancing statistical stability can rectify this issue. Inspired by that, a simple yet effective approach is proposed, known as group sampling, which gathers groups of samples from the same class into a mini-batch. The model is thereby trained using normalized group samples, which helps to alleviate the effects associated with a single sample. Group sampling updates the pipeline of pseudo label generation by guaranteeing that samples are more efficiently divided into the correct classes. Group sampling regulates the representation learning process, which enhances statistical stability for feature representation in a progressive fashion. Qualitative and quantitative experiments on Market-1501, DukeMTMC-reID, and MSMT17 show that group sampling improves upon state-of-the-art methods by between 3.3%~6.1%. Code has been available at this https URL.