Semi-Supervised Learning With GANs: Revisiting Manifold Regularization

Bruno Lecouat, Chuan Sheng Foo, Houssam Zenati, Vijay Ramaseshan Chandrasekhar

Abstract: 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 Salimans et al. (2016), we achieve state-of-the-art results for GAN-based semisupervised learning on the CIFAR-10 dataset, with a method that is significantly easier to implement than competing methods.