PersonNet: Person Re-identification with Deep Convolutional Neural Networks

TL;DR

PersonNet introduces a deep convolutional neural network that learns high-level features and similarity metrics for person re-identification, achieving superior performance on multiple large datasets.

Contribution

The paper presents a novel end-to-end deep neural network architecture with neighborhood range difference layers and RMSProp optimization for improved person re-identification.

Findings

Outperforms state-of-the-art on CUHK03 and Market-1501 datasets

Uses a 10-layer deep architecture with small convolution filters

Achieves significant accuracy improvements over prior methods

Abstract

In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification. The network takes a pair of raw RGB images as input, and outputs a similarity value indicating whether the two input images depict the same person. A layer of computing neighborhood range differences across two input images is employed to capture local relationship between patches. This operation is to seek a robust feature from input images. By increasing the depth to 10 weight layers and using very small (3$\times$3) convolution filters, our architecture achieves a remarkable improvement on the prior-art configurations. Meanwhile, an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into our architecture, which is beneficial to deep nets. Our method consistently outperforms state-of-the-art on two large datasets (CUHK03 and Market-1501), and a medium-sized data set (CUHK01).