M3L: Multi-modality mining for metric learning in person re-Identification

Learning a scene-specific distance metric from labeled data is critical for person re-identification. Most of the earlier works in this area aim to seek a linear transformation of the feature space such that relevant dimensions are emphasized while irrelevant ones are discarded in a global sense. However, when training data exhibit multi-modality transitions, the globally learned metric would deviate from the correct metrics learned from each modality. In this study, we propose a multi-modality mining approach for metric learning (M3L) to automatically discover multiple modalities of illumination changes by exploring the shift-invariant property in log-chromaticity space, and then learn a sub-metric for each modality to maximally reduce the bias derived from metric learning model with global sense. The experiments on the challenging VIPeR dataset and the fusion dataset VIPeR&PRID 450S have validated the effectiveness of the proposed method with an average improvement of 2-7% over original baseline methods.