Dynamic Label Graph Matching for Unsupervised Video Re-Identification

Mang Ye, Andy J. Ma, Liang Zheng, Jiawei Li, Pong C. Yuen; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5142-5150

Abstract


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 propose 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Ye_2017_ICCV,
author = {Ye, Mang and Ma, Andy J. and Zheng, Liang and Li, Jiawei and Yuen, Pong C.},
title = {Dynamic Label Graph Matching for Unsupervised Video Re-Identification},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}