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

Shabab Bazrafkan; Hossein Javidnia; Peter Corcoran

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

Image and Video Processing 2018-06-20 v3 Computer Vision and Pattern Recognition Machine Learning

Authors: Shabab Bazrafkan , Hossein Javidnia , Peter Corcoran

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.

Keywords

generative adversarial networks generative adversarial networks for speech machine learning

Cite

@article{arxiv.1805.00316,
  title  = {Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)},
  author = {Shabab Bazrafkan and Hossein Javidnia and Peter Corcoran},
  journal= {arXiv preprint arXiv:1805.00316},
  year   = {2018}
}

Comments

This paper will be uploaded as two separate manuscripts

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

Abstract

Keywords

Cite

Comments

Related papers