Semi-supervised Region Metric Learning for Person Re-identification

Jiawei Li, Andy J. Ma, Pong C. Yuen*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

47 Citations (Scopus)


In large-scale camera networks, label information for person re-identification is usually not available under a large amount of cameras due to expensive human labor efforts. Semi-supervised learning could be employed to train a discriminative classifier by using unlabeled data and unmatched image pairs (negatives) generated from non-overlapping camera views, but existing methods suffer from the problem of imbalanced unlabeled data. In this context, this paper proposes a novel semi-supervised region metric learning method to improve person re-identification performance under imbalanced unlabeled data. Firstly, instead of seeking for matched image pairs (positives) from the unlabeled data, we propose to estimate positive neighbors by label propagation with cross person score distribution alignment. Secondly, multiple positive regions are generated using sets of positive neighbors to learn a discriminative region-to-point metric. Experimental results demonstrate that the superiority of the proposed method over existing unsupervised, semi-supervised and person re-identification methods.

Original languageEnglish
Pages (from-to)855-874
Number of pages20
JournalInternational Journal of Computer Vision
Issue number8
Early online date27 Mar 2018
Publication statusPublished - Aug 2018

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

User-Defined Keywords

  • Imbalanced unlabeled data
  • Person re-identification
  • Semi-supervised learning


Dive into the research topics of 'Semi-supervised Region Metric Learning for Person Re-identification'. Together they form a unique fingerprint.

Cite this