Coupled metric learning for single-shot versus single-shot person reidentification

Abstract. Person reidentification tackles the problem of building a correspondence between different images of the same person captured by distributed cameras. To date, attempts to solve this problem have focused on either feature representation or learning methods. Usually, the greater the number of the samples for each person, the better the reidentification performance is. However, in the real world, we may not be able to acquire enough samples to give acceptable performance. Here, we focus on the so-called “single-shot versus single-shot” problem: matching one image of a person to another. Because of the extremely small sample class size, there is limited scope to statistically weaken the empirical risk for hand-crafted feature representation. Therefore, we resort to metric learning methods, such as the ranking-specialized metric learning to rank (MLR) and the classification-based maximally collapsing metric learning (MCML). Taking advantage of the complementarity between them, we propose a novel “coupled metric learning” approach. This searches for the optimal linear projection for the original feature space using MCML before minimizing the ranking loss via MLR. Experiments on widely used benchmark datasets show encouraging results.