Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
arXiv:1902.03442 · doi:10.2352/ISSN.2470-1173.2019.15.AVM-048
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.
Accepted for publication in Electronic Imaging, Autonomous Vehicles and Machines 2019. arXiv admin note: text overlap with arXiv:1606.05908 by other authors
References in corpus (26)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Explaining and Harnessing Adversarial Examples
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Self-Attention Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Semi-Supervised Learning with Deep Generative Models
- Tutorial on Variational Autoencoders
- NIPS 2016 Tutorial: Generative Adversarial Networks
- DeepXplore: Automated Whitebox Testing of Deep Learning Systems
- Toward Multimodal Image-to-Image Translation
- Generating Videos with Scene Dynamics
- Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
- Multimodal Unsupervised Image-to-Image Translation
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
- DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
- How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
- Virtual to Real Reinforcement Learning for Autonomous Driving
- Video-to-Video Synthesis
- Context-Aware Synthesis and Placement of Object Instances
- Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
- Point Cloud GAN