Semi-Supervised Learning with Generative Adversarial Networks
Machine Learning
2016-10-25 v2 Machine Learning
Abstract
We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. We show that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.
Cite
@article{arxiv.1606.01583,
title = {Semi-Supervised Learning with Generative Adversarial Networks},
author = {Augustus Odena},
journal= {arXiv preprint arXiv:1606.01583},
year = {2016}
}
Comments
Appearing in the Data Efficient Machine Learning workshop at ICML 2016