English

PersonNet: Person Re-identification with Deep Convolutional Neural Networks

Computer Vision and Pattern Recognition 2016-06-21 v2

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×\times3) 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).

Keywords

Cite

@article{arxiv.1601.07255,
  title  = {PersonNet: Person Re-identification with Deep Convolutional Neural Networks},
  author = {Lin Wu and Chunhua Shen and Anton van den Hengel},
  journal= {arXiv preprint arXiv:1601.07255},
  year   = {2016}
}

Comments

7 pages. Fixed Figure 4 (a)

R2 v1 2026-06-22T12:37:32.175Z