Distance Learning by Mining Hard and Easy Negative Samples for Person Re-identification

Abstract Distance learning is an effective technique for person re-identification. In practice, the hard negative samples usually contain more discriminative information than the easy negative samples. Therefore, it’s necessary to investigate how to make full use of the discriminative information conveyed by different types of negative samples in the distance learning process. In this paper, we propose a Hard and Easy Negative samples mining based Distance learning (HEND) approach for person re-identification, which learns the distance metric by designing different objective functions for hard and easy negative samples, such that the discriminative information contained in negative samples can be exploited more effectively. Moreover, considering that there usually exist large differences between the images captured by different cameras, we further propose a projection-based HEND approach to reduce the influence of between-camera differences to the re-identification. Experimental results on seven pedestrian image datasets demonstrate the effectiveness of the proposed approaches.