Class-Splitting Generative Adversarial Networks

by   Guillermo L. Grinblat, et al.

Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still observed for the recently proposed Wasserstein GAN formulation which stabilized adversarial training and allows considering high capacity network architectures such as ResNet. In this work we show how to boost conditional GAN by augmenting available class labels. The new classes come from clustering in the representation space learned by the same GAN model. The proposed strategy is also feasible when no class information is available, i.e. in the unsupervised setup. Our generated samples reach state-of-the-art Inception scores for CIFAR-10 and STL-10 datasets in both supervised and unsupervised setup.


page 1

page 2

page 3

page 4

page 6

page 7


Label-Noise Robust Generative Adversarial Networks

Generative adversarial networks (GANs) are a framework that learns a gen...

Virtual Conditional Generative Adversarial Networks

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

Activation Maximization Generative Adversarial Nets

Class label information has been empirically proven to be very useful in...

3D Semantic Scene Completion from a Single Depth Image using Adversarial Training

We address the task of 3D semantic scene completion, i.e. , given a sing...

Collapse by Conditioning: Training Class-conditional GANs with Limited Data

Class-conditioning offers a direct means of controlling a Generative Adv...

Using General Adversarial Networks for Marketing: A Case Study of Airbnb

In this paper, we examine the use case of general adversarial networks (...

Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks

Designing a logo for a new brand is a lengthy and tedious back-and-forth...

Code Repositories


Code for Class-Splitting Generative Adversarial Networks

view repo

Please sign up or login with your details

Forgot password? Click here to reset