Constrained Deep Metric Learning for Person Re-identification

TL;DR

This paper introduces a CNN-based person re-identification method that employs a constrained Mahalanobis metric and a novel training strategy to improve robustness and reduce over-fitting, achieving superior results on benchmark datasets.

Contribution

It proposes a new deep architecture with a weight-constrained Mahalanobis metric and a moderate positive mining strategy to enhance generalization in person re-identification.

Findings

Significantly outperforms existing methods on multiple benchmarks.

The weight constraint improves the generalization of the learned metric.

Moderate positive mining effectively handles intra-class variations.

Abstract

Person re-identification aims to re-identify the probe image from a given set of images under different camera views. It is challenging due to large variations of pose, illumination, occlusion and camera view. Since the convolutional neural networks (CNN) have excellent capability of feature extraction, certain deep learning methods have been recently applied in person re-identification. However, in person re-identification, the deep networks often suffer from the over-fitting problem. In this paper, we propose a novel CNN-based method to learn a discriminative metric with good robustness to the over-fitting problem in person re-identification. Firstly, a novel deep architecture is built where the Mahalanobis metric is learned with a weight constraint. This weight constraint is used to regularize the learning, so that the learned metric has a better generalization ability. Secondly, we find that the selection of intra-class sample pairs is crucial for learning but has received little attention. To cope with the large intra-class variations in pedestrian images, we propose a novel training strategy named moderate positive mining to prevent the training process from over-fitting to the extreme samples in intra-class pairs. Experiments show that our approach significantly outperforms state-of-the-art methods on several benchmarks of person re-identification.