# Deep Metric Learning for Practical Person Re-Identification

arXiv: https://arxiv.org/abs/1407.4979 · HTML: https://mlsanity.com/paper/1407.4979/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2014.

## Built on by (most cited first, 3 of 3)

- [It Takes Two to Tango: Mixup for Deep Metric Learning](https://mlsanity.com/paper/2106.04990/) (2021)
- [Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Review](https://mlsanity.com/paper/2102.09744/) (2021)
- [Rethinking Deep Contrastive Learning with Embedding Memory](https://mlsanity.com/paper/2103.14003/) (2021)

## Abstract (arXiv)

Various hand-crafted features and metric learning methods prevail in the field of person re-identification. Compared to these methods, this paper proposes a more general way that can learn a similarity metric from image pixels directly. By using a "siamese" deep neural network, the proposed method can jointly learn the color feature, texture feature and metric in a unified framework. The network has a symmetry structure with two sub-networks which are connected by Cosine function. To deal with the big variations of person images, binomial deviance is used to evaluate the cost between similarities and labels, which is proved to be robust to outliers. Compared to existing researches, a more practical setting is studied in the experiments that is training and test on different datasets (cross dataset person re-identification). Both in "intra dataset" and "cross dataset" settings, the superiorities of the proposed method are illustrated on VIPeR and PRID.