# Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving

## TL;DR

This paper reviews how Generative Adversarial Networks (GANs) are applied to autonomous driving, highlighting their roles in data augmentation, loss function learning, and semi-supervised learning, while discussing current challenges.

## Contribution

It formalizes and reviews key applications of GANs in autonomous driving, emphasizing their impact and identifying open challenges in the field.

## Key findings

- GANs improve data augmentation for autonomous driving
- Adversarial techniques enhance semi-supervised learning in autonomous systems
- Discussion of open problems guides future research directions

## Abstract

Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed.