Dynamic Label Graph Matching for Unsupervised Video Re-Identification
This addresses label estimation for unsupervised person re-identification, which is incremental as it builds on existing graph matching methods.
The paper tackles the problem of cross-camera label estimation for unsupervised person re-identification by proposing a dynamic graph matching method that iteratively updates graphs and labels to improve accuracy and robustness to noise, achieving competitive performance with supervised baselines on benchmarks like MARS.
Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods.