papers AI Learner
The Github is limit! Click to go to the new site.

Manifold regularization with GANs for semi-supervised learning

2018-07-11
Bruno Lecouat, Chuan-Sheng Foo, Houssam Zenati, Vijay Chandrasekhar

Abstract

Generative Adversarial Networks are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating a variant of the Laplacian norm using a Monte Carlo approximation that is easily computed with the GAN. When incorporated into the semi-supervised feature-matching GAN we achieve state-of-the-art results for GAN-based semi-supervised learning on CIFAR-10 and SVHN benchmarks, with a method that is significantly easier to implement than competing methods. We also find that manifold regularization improves the quality of generated images, and is affected by the quality of the GAN used to approximate the regularizer.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1807.04307

PDF

https://arxiv.org/pdf/1807.04307


Similar Posts

Comments