Hierarchical Mixtures of Generators for Adversarial Learning

11/05/2019
by   Alper Ahmetoğlu, et al.
22

Generative adversarial networks (GANs) are deep neural networks that allow us to sample from an arbitrary probability distribution without explicitly estimating the distribution. There is a generator that takes a latent vector as input and transforms it into a valid sample from the distribution. There is also a discriminator that is trained to discriminate such fake samples from true samples of the distribution; at the same time, the generator is trained to generate fakes that the discriminator cannot tell apart from the true samples. Instead of learning a global generator, a recent approach involves training multiple generators each responsible from one part of the distribution. In this work, we review such approaches and propose the hierarchical mixture of generators, inspired from the hierarchical mixture of experts model, that learns a tree structure implementing a hierarchical clustering with soft splits in the decision nodes and local generators in the leaves. Since the generators are combined softly, the whole model is continuous and can be trained using gradient-based optimization, just like the original GAN model. Our experiments on five image data sets, namely, MNIST, FashionMNIST, UTZap50K, Oxford Flowers, and CelebA, show that our proposed model generates samples of high quality and diversity in terms of popular GAN evaluation metrics. The learned hierarchical structure also leads to knowledge extraction.

READ FULL TEXT

page 5

page 7

page 8

research
04/10/2017

Multi-Agent Diverse Generative Adversarial Networks

This paper describes an intuitive generalization to the Generative Adver...
research
07/01/2020

Sliced Iterative Generator

We introduce the Sliced Iterative Generator (SIG), an iterative generati...
research
12/06/2021

Top-Down Deep Clustering with Multi-generator GANs

Deep clustering (DC) leverages the representation power of deep architec...
research
05/07/2018

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

Recently, generative adversarial networks (GANs) have shown promising pe...
research
02/09/2019

Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions

We propose a GAN design which models multiple distributions effectively ...
research
02/16/2016

Generating images with recurrent adversarial networks

Gatys et al. (2015) showed that optimizing pixels to match features in a...
research
11/05/2019

Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views

In this paper, we present a conditional GAN with two generators and a co...

Please sign up or login with your details

Forgot password? Click here to reset