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.

Keywords: Generative Adversarial Networks, Semi Supervised Learning