GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplacian norm using a Monte Carlo approximation that is easily computed with the GAN. When incorporated into the feature-matching GAN of Improved GAN, we achieve state-of-the-art results for GAN-based semi-supervised learning on the CIFAR-10 dataset, with a method that is significantly easier to implement than competing methods.
@article{arxiv.1805.08957,
title = {Semi-Supervised Learning with GANs: Revisiting Manifold Regularization},
author = {Bruno Lecouat and Chuan-Sheng Foo and Houssam Zenati and Vijay R. Chandrasekhar},
journal= {arXiv preprint arXiv:1805.08957},
year = {2018}
}