A Review on Generative Adversarial Networks for Data Augmentation in Person Re-Identification Systems

TL;DR

This paper reviews recent advances in using generative adversarial networks for data augmentation to enhance person re-identification systems, addressing challenges like variability in appearance and image quality.

Contribution

It categorizes and analyzes recent GAN-based data augmentation methods—style transfer, pose transfer, and random generation—for person re-identification.

Findings

GAN-based augmentation improves re-identification accuracy

Style transfer enhances appearance variability

Pose transfer simulates different postures

Abstract

Interest in automatic people re-identification systems has significantly grown in recent years, mainly for developing surveillance and smart shops software. Due to the variability in person posture, different lighting conditions, and occluded scenarios, together with the poor quality of the images obtained by different cameras, it is currently an unsolved problem. In machine learning-based computer vision applications with reduced data sets, one possibility to improve the performance of re-identification system is through the augmentation of the set of images or videos available for training the neural models. Currently, one of the most robust ways to generate synthetic information for data augmentation, whether it is video, images or text, are the generative adversarial networks. This article reviews the most relevant recent approaches to improve the performance of person re-identification models through data augmentation, using generative adversarial networks. We focus on three categories of data augmentation approaches: style transfer, pose transfer, and random generation.