Equidistance constrained metric learning for person re-identification. (February 2018)

• Record Type: Journal Article
• Authors: Wang, Jin; Wang, Zheng; Liang, Chao; Gao, Changxin; Sang, Nong
• Is Part Of: Pattern recognition. Volume 74(2018:Feb.)
• Page Start: 38
• Page End: 51
• Publication Date: 2018-02
• Subjects: Person re-identification -- Metric learning -- Equidistance embedding; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.09.014
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: An equidistance constrained metric learning algorithm for person re-identification is proposed. In our method, points of the same class are collapsed into a single point, while points of different classes are mapped to different vertices of a regular simplex. Our method aims to guarantee the best separability of the training data, meanwhile, promote the generalization ability of the learned metric. Abstract: Person re-identification (re-id), aiming to search a specific person among a non-overlapping camera network, has attracted plenty of interest in recent years. This task is highly challenging, especially when there exists only single image per person in the database. In this paper, we present an algorithm for learning a Mahalanobis distance for person re-identification. Our method has two distinctive features: (1) to obtain the best separability of the training data, we first minimize the intra-class distances to the most extent by forcing intra-class distances to be zero, and (2) to promote the generalization ability of the learned metric, we then maximize the minimum margin between different classes. Inspired by the simple geometric intuition that a regular simplex maximizes its minimum side length, provided the sum of all side length is fixed, our method, called EquiDistance constrained Metric Learning (EquiDML), applies least-square regression technique to map images of the same person to the same vertex of a regular simplex, and images of different persons to different vertices of a regular simplex. Consequently, under the learned metric, images of the same class are collapsed to a single point, while images of different classes are transformed to be equidistant. This simple motivation is further formulated as a convex optimization problem, solved by the projected gradient descent method and proved to be very effective in person re-identification task. Although it is fairly simple, our method outperforms the state-of-the-art methods on CUHK01, CUHK03, Market1501 and DukeMTMC-reID datasets, and achieves very competitive performance on the widely used VIPeR dataset.