Ensembles of Generative Adversarial Networks
This work addresses the challenge of enhancing GAN performance for generative modeling, but it is incremental as it applies ensemble techniques from discriminative models to GANs.
The paper tackled the problem of improving generative adversarial networks (GANs) by using ensembles, showing that ensembles of GANs better model data distributions on the CIFAR10 dataset with little additional computational cost.
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.