DeepAI AI Chat
Log In Sign Up

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

by   Matan Ben-Yosef, et al.
Hebrew University of Jerusalem

Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a better fit to the target data distribution when the dataset includes many different classes, we propose a variant of the basic GAN model, called Gaussian Mixture GAN (GM-GAN), where the probability distribution over the latent space is a mixture of Gaussians. We also propose a supervised variant which is capable of conditional sample synthesis. In order to evaluate the model's performance, we propose a new scoring method which separately takes into account two (typically conflicting) measures - diversity vs. quality of the generated data. Through a series of empirical experiments, using both synthetic and real-world datasets, we quantitatively show that GM-GANs outperform baselines, both when evaluated using the commonly used Inception Score, and when evaluated using our own alternative scoring method. In addition, we qualitatively demonstrate how the unsupervised variant of GM-GAN tends to map latent vectors sampled from different Gaussians in the latent space to samples of different classes in the data space. We show how this phenomenon can be exploited for the task of unsupervised clustering, and provide quantitative evaluation showing the superiority of our method for the unsupervised clustering of image datasets. Finally, we demonstrate a feature which further sets our model apart from other GAN models: the option to control the quality-diversity trade-off by altering, post-training, the probability distribution of the latent space. This allows one to sample higher quality and lower diversity samples, or vice versa, according to one's needs.


page 2

page 9

page 10

page 13

page 15


ClusterGAN : Latent Space Clustering in Generative Adversarial Networks

Generative Adversarial networks (GANs) have obtained remarkable success ...

MMGAN: Generative Adversarial Networks for Multi-Modal Distributions

Over the past years, Generative Adversarial Networks (GANs) have shown a...

ciDATGAN: Conditional Inputs for Tabular GANs

Conditionality has become a core component for Generative Adversarial Ne...

Ensembles of Generative Adversarial Networks for Disconnected Data

Most current computer vision datasets are composed of disconnected sets,...

Student's t-Generative Adversarial Networks

Generative Adversarial Networks (GANs) have a great performance in image...

An Improved Evaluation Framework for Generative Adversarial Networks

In this paper, we propose an improved quantitative evaluation framework ...