Deep Person Re-Identification with Improved Embedding and Efficient Training

TL;DR

This paper introduces an efficient deep learning approach for person re-identification that employs identification and center loss without pairs or triplets, and features a reweighting layer to enhance embedding quality, achieving superior accuracy and speed.

Contribution

It proposes a novel training method using identification and center loss, along with a feature reweighting layer, to improve re-identification performance efficiently.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Achieves higher accuracy with faster training.

Effectively emphasizes important embedding dimensions.

Abstract

Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is limited since they ignore the fact that different dimension of embedding may play different importance. In this paper, we propose to employ identification loss with center loss to train a deep model for person re-identification. The training process is efficient since it does not require image pairs or triplets for training while the inter-class distinction and intra-class variance are well handled. To boost the performance, a new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding. Experiments on several benchmark datasets have shown the superiority of our method over the state-of-the-art alternatives on both accuracy and speed.