Fast Momentum Contrast Learning for Unsupervised Person Re-Identification
Binquan Wang, Guoqi Ma, Ming Zhu
Abstract
Person re-identification (re-ID) aims to identify the same persons' images across different cameras by deploying a trained re-ID model. Nevertheless, the domain bias between different datasets can lead to considerably low identification accuracy when directly applying a trained re-ID model from one dataset to another. Therefore, in order to develop a kind of more transferable re-ID methods with strong robustness, this paper proposes a fast momentum contrast learning framework, which consists of a teacher encoder and a fast momentum encoder, from a reinforcing visual representation learning point of view. The fast momentum encoder produced by the teacher encoder is employed to build a dynamic dictionary and then design the contrast learning loss function together with the teacher encoder. In addition, both the individual loss and the clustering loss are adopted for obtaining the optimal performances in unsupervised person re-ID models. The proposed framework achieves one stage of end-to-end training and experimental results demonstrate that our identification accuracy outperforms existing advanced methods.