Deep Metric Learning for Practical Person Re-Identification

TL;DR

This paper introduces a deep neural network approach for person re-identification that learns similarity metrics directly from raw images, demonstrating robustness and superior performance across different datasets.

Contribution

It proposes a unified deep learning framework that jointly learns features and metrics for person re-identification, including a symmetry structure and robust cost evaluation.

Findings

Outperforms existing methods on VIPeR and PRID datasets

Effective in cross-dataset re-identification scenarios

Robust to outliers due to binomial deviance

Abstract

Various hand-crafted features and metric learning methods prevail in the field of person re-identification. Compared to these methods, this paper proposes a more general way that can learn a similarity metric from image pixels directly. By using a "siamese" deep neural network, the proposed method can jointly learn the color feature, texture feature and metric in a unified framework. The network has a symmetry structure with two sub-networks which are connected by Cosine function. To deal with the big variations of person images, binomial deviance is used to evaluate the cost between similarities and labels, which is proved to be robust to outliers. Compared to existing researches, a more practical setting is studied in the experiments that is training and test on different datasets (cross dataset person re-identification). Both in "intra dataset" and "cross dataset" settings, the superiorities of the proposed method are illustrated on VIPeR and PRID.