Semi-Supervised Learning With GANs: Revisiting Manifold RegularizationDownload PDF

12 Feb 2018, 21:58 (modified: 04 Jun 2018, 15:00)ICLR 2018 Workshop SubmissionReaders: Everyone
Keywords: Generative Adversarial Networks, Semi Supervised Learning
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.
4 Replies