DeepAI AI Chat
Log In Sign Up

Disconnected Manifold Learning for Generative Adversarial Networks

by   Mahyar Khayatkhoei, et al.
Rutgers University
Verisk Analytics

Real images often lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work, we first show that single generator GANs are unable to correctly model a distribution supported on a disconnected manifold, and investigate how sample quality, mode collapse and local convergence are affected by this. Next, we show how using a collection of generators can address this problem, providing new insights into the success of such multi-generator GANs. Finally, we explain the serious issues caused by considering a fixed prior over the collection of generators and propose a novel approach for learning the prior and inferring the necessary number of generators without any supervision. Our proposed modifications can be applied on top of any other GAN model to enable learning of distributions supported on disconnected manifolds. We conduct several experiments to illustrate the aforementioned shortcoming of GANs, its consequences in practice, and the effectiveness of our proposed modifications in alleviating these issues.


page 8

page 15

page 16

page 17

page 18


MR-GAN: Manifold Regularized Generative Adversarial Networks

Despite the growing interest in generative adversarial networks (GANs), ...

Learning disconnected manifolds: a no GANs land

Typical architectures of Generative AdversarialNetworks make use of a un...

Partition-Guided GANs

Despite the success of Generative Adversarial Networks (GANs), their tra...

Global versus Localized Generative Adversarial Nets

In this paper, we present a novel localized Generative Adversarial Net (...

Top-Down Deep Clustering with Multi-generator GANs

Deep clustering (DC) leverages the representation power of deep architec...

Improving Generative Adversarial Networks with Local Coordinate Coding

Generative adversarial networks (GANs) have shown remarkable success in ...

Generating and Aligning from Data Geometries with Generative Adversarial Networks

Unsupervised domain mapping has attracted substantial attention in recen...

Code Repositories


Disconnected Manifold Learning for Generative Adversarial Networks.

view repo