# PersonNet: Person Re-identification with Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1601.07255 · HTML: https://mlsanity.com/paper/1601.07255/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2016.

## Built on by (most cited first, 9 of 9)

- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Learning to Generate Image Embeddings with User-level Differential Privacy](https://mlsanity.com/paper/2211.10844/) (2022)
- [Pose Invariant Person Re-Identification using Robust Pose-transformation GAN](https://mlsanity.com/paper/2105.00930/) (2021)
- [Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification](https://mlsanity.com/paper/2207.14243/) (2022)
- [Style Variable and Irrelevant Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2209.05235/) (2022)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification](https://mlsanity.com/paper/2104.13780/) (2021)
- [DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.06600/) (2024)
- [CowCare: A Unified Visual Framework for Viewpoint-Robust Cattle Tracking and Spatiotemporal Heat-Stress Analysis](https://mlsanity.com/paper/2610.15012/) (2026)

## Abstract (arXiv)

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 (3×3) 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).