Ensembles of Generative Adversarial Networks for Disconnected Data

by   Lorenzo Luzi, et al.

Most current computer vision datasets are composed of disconnected sets, such as images from different classes. We prove that distributions of this type of data cannot be represented with a continuous generative network without error. They can be represented in two ways: With an ensemble of networks or with a single network with truncated latent space. We show that ensembles are more desirable than truncated distributions in practice. We construct a regularized optimization problem that establishes the relationship between a single continuous GAN, an ensemble of GANs, conditional GANs, and Gaussian Mixture GANs. This regularization can be computed efficiently, and we show empirically that our framework has a performance sweet spot which can be found with hyperparameter tuning. This ensemble framework allows better performance than a single continuous GAN or cGAN while maintaining fewer total parameters.


page 1

page 2

page 3

page 4


Ensembles of Generative Adversarial Networks

Ensembles are a popular way to improve results of discriminative CNNs. T...

Generative Ensemble-Regression: Learning Stochastic Dynamics from Discrete Particle Ensemble Observations

We propose a new method for inferring the governing stochastic ordinary ...

Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images

Generative Adversarial Networks (GANs) have been shown to produce realis...

Stein Latent Optimization for GANs

Generative adversarial networks (GANs) with clustered latent spaces can ...

Virtual Conditional Generative Adversarial Networks

When trained on multimodal image datasets, normal Generative Adversarial...

Re-purposing Heterogeneous Generative Ensembles with Evolutionary Computation

Generative Adversarial Networks (GANs) are popular tools for generative ...

Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations

The Generative Adversarial Network (GAN) is a powerful and flexible tool...

Please sign up or login with your details

Forgot password? Click here to reset