Unsupervised Person Re-Identification Using Multi-Branch Feature Compensation Network and Link-Based Cluster Dissimilarity Metric

Lin Pan, Gege Qi, Biao Guo, Yuesheng ZhuICASSP 2020 · OpenReview

Abstract

Feature extraction and label estimation are critical in unsupervised person re-identification (re-ID). Most previous works focus on acquiring high-layer semantic features and reckon without the lower-layer details lost in the learning process, which causes the extracted features to be less comprehensive and may degrade re-ID performance. Therefore in this paper, a Multi-branch Feature Compensation Network (MFC-Net) is developed in which the significant parts of lower-layer features are learned and fused with high-layer feature as compensation. Moreover, to accurately conduct label estimation through applying hierarchical clustering on individual samples, a Link-based Cluster Dissimilarity Metric (LCDM) is proposed to discover the inner correlation between clusters. These two methods are later integrated as a MFC-LCDM scheme to improve unsupervised re-ID performance. Extensive experiments on large-scale image-based and video-based datasets ulteriorly demonstrate the superiority and effectiveness of MFC-LCDM.
BibTeX
@inproceedings{pan2020unsupervised,
  author = {Lin Pan and Gege Qi and Biao Guo and Yuesheng Zhu},
  title = {{Unsupervised Person Re-Identification Using Multi-Branch Feature Compensation Network and Link-Based Cluster Dissimilarity Metric}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  url = {https://openreview.net/forum?id=7PH1swnld4},
}

Loading related content...

Figure