DeepAI AI Chat

Unrolled Generative Adversarial Networks

11/07/2016

∙

by Luke Metz, et al.

∙

Google

∙

Stanford University

∙

∙

We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of the data distribution by the generator.

Luke Metz
30 publications
Ben Poole
34 publications
David Pfau
14 publications
Jascha Sohl-Dickstein
68 publications

page 6

page 8

page 19

page 21

page 22

page 23

page 24

page 25

∙ 10/30/2019

Investigating Under and Overfitting in Wasserstein Generative Adversarial Networks

We investigate under and overfitting in Generative Adversarial Networks ...

0 Ben Adlam, et al. ∙

∙ 10/25/2018

Training Generative Adversarial Networks Via Turing Test

In this article, we introduce a new mode for training Generative Adversa...

2 Jianlin Su, et al. ∙

∙ 07/30/2018

Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators

We propose to incorporate adversarial dropout in generative multi-advers...

0 Gonçalo Mordido, et al. ∙

∙ 07/18/2017

Optimizing the Latent Space of Generative Networks

Generative Adversarial Networks (GANs) have been shown to be able to sam...

0 Piotr Bojanowski, et al. ∙

∙ 11/14/2022

Shared Loss between Generators of GANs

Generative adversarial networks are generative models that are capable o...

0 Xin Wang, et al. ∙

∙ 07/07/2019

Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks

In this study, we employ Generative Adversarial Networks as an oversampl...

0 Hung Ba, et al. ∙

∙ 05/25/2023

Learning and accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks

Generative Adversarial Networks (GANs) have shown immense potential in f...

0 Daniele Lanzoni, et al. ∙

Code Repositories

unrolled_gan

Unrolled Generative Adversarial Networks

view repo

gradient_regularized_gan

Code for "Gradient descent GAN optimization is locally stable"

view repo