PersonNet: Person Re-identification with Deep Convolutional Neural Networks
This addresses the problem of identifying individuals across different camera views for surveillance and security applications, representing an incremental improvement over prior methods.
The paper tackles person re-identification by proposing PersonNet, a deep end-to-end neural network that learns features and similarity metrics from raw RGB image pairs, achieving state-of-the-art performance on datasets like CUHK03, Market-1501, and CUHK01.
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).