Lessons Learned from the Training of GANs on Artificial Datasets

by   Shichang Tang, et al.

Generative Adversarial Networks (GANs) have made great progress in synthesizing realistic images in recent years. However, they are often trained on image datasets with either too few samples or too many classes belonging to different data distributions. Consequently, GANs are prone to underfitting or overfitting, making the analysis of them difficult and constrained. Therefore, in order to conduct a thorough study on GANs while obviating unnecessary interferences introduced by the datasets, we train them on artificial datasets where there are infinitely many samples and the real data distributions are simple, high-dimensional and have structured manifolds. Moreover, the generators are designed such that optimal sets of parameters exist. Empirically, we find that under various distance measures, the generator fails to learn such parameters with the GAN training procedure. We also find that training mixtures of GANs leads to more performance gain compared to increasing the network depth or width when the model complexity is high enough. Our experimental results demonstrate that a mixture of generators can discover different modes or different classes automatically in an unsupervised setting, which we attribute to the distribution of the generation and discrimination tasks across multiple generators and discriminators. As an example of the generalizability of our conclusions to realistic datasets, we train a mixture of GANs on the CIFAR-10 dataset and our method significantly outperforms the state-of-the-art in terms of popular metrics, i.e., Inception Score (IS) and Fréchet Inception Distance (FID).


page 1

page 4

page 5

page 6

page 8

page 9

page 10


Score-Guided Generative Adversarial Networks

We propose a Generative Adversarial Network (GAN) that introduces an eva...

Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks

We propose an approach to address two issues that commonly occur during ...

Partition-Guided GANs

Despite the success of Generative Adversarial Networks (GANs), their tra...

Slimmable Generative Adversarial Networks

Generative adversarial networks (GANs) have achieved remarkable progress...

The Unusual Effectiveness of Averaging in GAN Training

We show empirically that the optimal strategy of parameter averaging in ...

MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation

Recently, generative adversarial networks (GANs) have shown promising pe...

Approximation for Probability Distributions by Wasserstein GAN

In this paper, we show that the approximation for distributions by Wasse...

Please sign up or login with your details

Forgot password? Click here to reset