Semi-supervised Conditional GANs
Machine Learning
2017-08-22 v1 Machine Learning
Abstract
We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models.
Cite
@article{arxiv.1708.05789,
title = {Semi-supervised Conditional GANs},
author = {Kumar Sricharan and Raja Bala and Matthew Shreve and Hui Ding and Kumar Saketh and Jin Sun},
journal= {arXiv preprint arXiv:1708.05789},
year = {2017}
}