English

Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering

Computer Vision and Pattern Recognition 2021-06-11 v1

Abstract

Unsupervised video-based person re-identification (re-ID) methods extract richer features from video tracklets than image-based ones. The state-of-the-art methods utilize clustering to obtain pseudo-labels and train the models iteratively. However, they underestimate the influence of two kinds of frames in the tracklet: 1) noise frames caused by detection errors or heavy occlusions exist in the tracklet, which may be allocated with unreliable labels during clustering; 2) the tracklet also contains hard frames caused by pose changes or partial occlusions, which are difficult to distinguish but informative. This paper proposes a Noise and Hard frame Aware Clustering (NHAC) method. NHAC consists of a graph trimming module and a node re-sampling module. The graph trimming module obtains stable graphs by removing noise frame nodes to improve the clustering accuracy. The node re-sampling module enhances the training of hard frame nodes to learn rich tracklet information. Experiments conducted on two video-based datasets demonstrate the effectiveness of the proposed NHAC under the unsupervised re-ID setting.

Keywords

Cite

@article{arxiv.2106.05441,
  title  = {Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering},
  author = {Pengyu Xie and Xin Xu and Zheng Wang and Toshihiko Yamasaki},
  journal= {arXiv preprint arXiv:2106.05441},
  year   = {2021}
}

Comments

Appearing at ICME 2021