Adaptive Metric Learning for People Re-Identification

作者：Zhang Guanwen^*; Kato Jien; Wang Yu; Mase Kenji

来源：IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2014, E97D(11): 2888-2902.

DOI：10.1587/transinf.2013EDP7451

• multiple-shot people re-identification
• adaptive metric learning
• local distance comparison

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.

• 出版日期2014-11