Abstract
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 Frechet Inception Distance (FID).
Highlights
The past few years have witnessed the arising popularity of generative models
Generative Adversarial Network [2], with no doubt, is the most prevailing generative model. It is composed of a generator G that maps random noise to synthesized data points, and a discriminator D which aims to tell whether its input comes from the real data distribution Pr or the generative distribution Pg
While current state-of-theart Generative Adversarial Networks (GANs) models on ImageNet are still subject to model complexity and batch size, our work focus on synthetic datasets that allows the batch size and model complexity to be sufficiently high, which enables us to explore the properties of GANs in ideal cases
Summary
The past few years have witnessed the arising popularity of generative models. Image processing (e.g., image super-resolution and editing) and machine learning (e.g., reinforcement learning and semi-supervised learning) tasks are infused strong energy by generative models [1]. A generative model learns a distribution Pg to approximate the true distribution Pr , given a set of observed samples. Generative Adversarial Network [2], with no doubt, is the most prevailing generative model. It is composed of a generator G that maps random noise to synthesized data points, and a discriminator D which aims to tell whether its input comes from the real data distribution Pr or the generative distribution Pg. During training, D and G are updated simultaneously or alternatingly. In a vanilla GAN, D gives an estimate of the Jensen-Shannon divergence between Pr and Pg while G tries to minimize it [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
