Dynamic Graph Co-Matching for Unsupervised Video-Based Person Re-Identification

Abstract

Cross-camera label estimation from a set of unlabeled training data is an extremely important component in the unsupervised person re-identification (re-ID) systems. With the estimated labels, the existing advanced supervised learning methods can be leveraged to learn discriminative re-ID models. In this paper, we utilize the graph matching technique for accurate label estimation due to its advantages in optimal global matching and intra-camera relationship mining. However, the graph structure constructed with non-learned similarity measurement cannot handle the large cross-camera variations, which leads to noisy and inaccurate label outputs. This paper designs a dynamic graph matching (DGM) framework, which improves the label estimation process by iteratively refining the graph structure with better similarity measurement learned from the intermediate estimated labels. In addition, we design a positive re-weighting strategy to refine the intermediate labels, which enhances the robustness against inaccurate matching output and noisy initial training data. To fully utilize the abundant video information and reduce false matchings, a co-matching strategy is further incorporated into the framework. Comprehensive experiments conducted on three video benchmarks demonstrate that DGM outperforms the state-of-the-art unsupervised re-ID methods and yields the competitive performance to fully supervised upper bounds.