Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2022

Abstract

In this paper, we propose a new approach to train Gen-erative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discrim-inator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response or-acles. We then compute the meta-strategies using a linear program. For scalability of the framework where multi-ple generators and discriminator best responses are stored in the memory, we propose two solutions: 1) pruning the weakly-dominated players' strategies to keep the oracles from becoming intractable; 2) applying continual learning to retain the previous knowledge of the networks. We apply our framework to established GAN architectures such as vanilla GAN, Deep Convolutional GAN, Spectral Normalization GAN and Stacked GAN. Finally, we conduct experiments on MNIST, CIFAR-10 and CelebA datasets and show that DO-GAN variants have significant improvements in both subjective qualitative evaluation and quantitative metrics, compared with their respective GAN architectures.

Keywords

Deep learning architectures and techniques, Image and video synthesis and generation, Optimization methods

Discipline

Artificial Intelligence and Robotics | Theory and Algorithms

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): New Orleans, June 18-24: Proceedings

First Page

11265

Last Page

11274

ISBN

9781665469463

Identifier

10.1109/CVPR52688.2022.01099

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR52688.2022.01099

Share

COinS