Ensembles of Generative Adversarial Networks

TL;DR

This paper explores novel ensemble methods for GANs, including self ensembles based on training iterations and cascade GANs redirecting poorly modeled data, demonstrating improved data distribution modeling with minimal extra cost.

Contribution

Introduces two new ensemble techniques for GANs—self ensembles and cascade GANs—that enhance data modeling efficiency and effectiveness.

Findings

Ensembles of GANs better model data distributions.

Self ensembles are faster to train than traditional ensembles.

Cascade GANs improve modeling of poorly generated data.

Abstract

Ensembles are a popular way to improve results of discriminative CNNs. The combination of several networks trained starting from different initializations improves results significantly. In this paper we investigate the usage of ensembles of GANs. The specific nature of GANs opens up several new ways to construct ensembles. The first one is based on the fact that in the minimax game which is played to optimize the GAN objective the generator network keeps on changing even after the network can be considered optimal. As such ensembles of GANs can be constructed based on the same network initialization but just taking models which have different amount of iterations. These so-called self ensembles are much faster to train than traditional ensembles. The second method, called cascade GANs, redirects part of the training data which is badly modeled by the first GAN to another GAN. In experiments on the CIFAR10 dataset we show that ensembles of GANs obtain model probability distributions which better model the data distribution. In addition, we show that these improved results can be obtained at little additional computational cost.