Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)

Abstract

One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. In this work, a new framework is presented to train a deep conditional generator by placing a classifier in parallel with the discriminator and back propagate the classification error through the generator network. The method is versatile and is applicable to any variations of Generative Adversarial Network (GAN) implementation, and also gives superior results compared to similar methods.

arXiv commentThis paper will be uploaded as two separate manuscripts

References in corpus (8)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Pixel Recurrent Neural Networks
• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks

Cited by in corpus (3)

• Deep Learning Based Computed Tomography Whys and Wherefores
• Versatile Auxiliary Regressor with Generative Adversarial network (VAR+GAN)
• Teaching a GAN What Not to Learn