Dynamic Graph Co-Matching for Unsupervised Video-Based Person Re-Identification

Mang Ye, Jiawei Li, Andy J. Ma, Liang Zheng, Pong Chi YUEN*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

64 Citations (Scopus)

Abstract

Cross-camera label estimation from a set of unlabeled training data is an extremely important component in the unsupervised person re-identification (re-ID) systems. With the estimated labels, the existing advanced supervised learning methods can be leveraged to learn discriminative re-ID models. In this paper, we utilize the graph matching technique for accurate label estimation due to its advantages in optimal global matching and intra-camera relationship mining. However, the graph structure constructed with non-learned similarity measurement cannot handle the large cross-camera variations, which leads to noisy and inaccurate label outputs. This paper designs a dynamic graph matching (DGM) framework, which improves the label estimation process by iteratively refining the graph structure with better similarity measurement learned from the intermediate estimated labels. In addition, we design a positive re-weighting strategy to refine the intermediate labels, which enhances the robustness against inaccurate matching output and noisy initial training data. To fully utilize the abundant video information and reduce false matchings, a co-matching strategy is further incorporated into the framework. Comprehensive experiments conducted on three video benchmarks demonstrate that DGM outperforms the state-of-the-art unsupervised re-ID methods and yields the competitive performance to fully supervised upper bounds.

Original languageEnglish
Article number8611378
Pages (from-to)2976-2990
Number of pages15
JournalIEEE Transactions on Image Processing
Volume28
Issue number6
DOIs
Publication statusPublished - Jun 2019

Scopus Subject Areas

  • Software
  • Computer Graphics and Computer-Aided Design

User-Defined Keywords

  • graph matching
  • Person Re-Identification
  • unsupervised learning

Fingerprint

Dive into the research topics of 'Dynamic Graph Co-Matching for Unsupervised Video-Based Person Re-Identification'. Together they form a unique fingerprint.

Cite this