Adaptive Metric Learning for People Re-Identification

Guanwen ZHANG  Jien KATO  Yu WANG  Kenji MASE  

IEICE TRANSACTIONS on Information and Systems   Vol.E97-D   No.11   pp.2888-2902
Publication Date: 2014/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2013EDP7451
Type of Manuscript: PAPER
Category: Image Processing and Video Processing
multiple-shot people re-identification,  adaptive metric learning,  local distance comparison,  

Full Text: PDF(3.1MB)>>
Buy this Article

There exist two intrinsic issues in multiple-shot person re-identification: (1) large differences in camera view, illumination, and non-rigid deformation of posture that make the intra-class variance even larger than the inter-class variance; (2) only a few training data that are available for learning tasks in a realistic re-identification scenario. In our previous work, we proposed a local distance comparison framework to deal with the first issue. In this paper, to deal with the second issue (i.e., to derive a reliable distance metric from limited training data), we propose an adaptive learning method to learn an adaptive distance metric, which integrates prior knowledge learned from a large existing auxiliary dataset and task-specific information extracted from a much smaller training dataset. Experimental results on several public benchmark datasets show that combined with the local distance comparison framework, our adaptive learning method is superior to conventional approaches.