DeepAI AI Chat
Log In Sign Up

On GANs and GMMs

by   Eitan Richardson, et al.
Hebrew University of Jerusalem

A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in particular have shown the ability to generate remarkably realistic high resolution sampled images. At the same time, many authors have pointed out that GANs may fail to model the full distribution ("mode collapse") and that using the learned models for anything other than generating samples may be very difficult. In this paper, we examine the utility of GANs in learning statistical models of images by comparing them to perhaps the simplest statistical model, the Gaussian Mixture Model. First, we present a simple method to evaluate generative models based on relative proportions of samples that fall into predetermined bins. Unlike previous automatic methods for evaluating models, our method does not rely on an additional neural network nor does it require approximating intractable computations. Second, we compare the performance of GANs to GMMs trained on the same datasets. While GMMs have previously been shown to be successful in modeling small patches of images, we show how to train them on full sized images despite the high dimensionality. Our results show that GMMs can generate realistic samples (although less sharp than those of GANs) but also capture the full distribution, which GANs fail to do. Furthermore, GMMs allow efficient inference and explicit representation of the underlying statistical structure. Finally, we discuss how a pix2pix network can be used to add high-resolution details to GMM samples while maintaining the basic diversity.


page 8

page 11

page 12

page 13

page 14

page 17

page 18

page 19


IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

We present a novel introspective variational autoencoder (IntroVAE) mode...

Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields

Generative adversarial networks (GANs) evolved into one of the most succ...

Evaluating the distribution learning capabilities of GANs

We evaluate the distribution learning capabilities of generative adversa...

Reconstruction of three-dimensional porous media using generative adversarial neural networks

To evaluate the variability of multi-phase flow properties of porous med...

GP-GAN: Towards Realistic High-Resolution Image Blending

Recent advances in generative adversarial networks (GANs) have shown pro...

Unsupervised Cipher Cracking Using Discrete GANs

This work details CipherGAN, an architecture inspired by CycleGAN used f...

Generating Synthetic but Plausible Healthcare Record Datasets

Generating datasets that "look like" given real ones is an interesting t...