Semi-Supervised Learning With GANs: Revisiting Manifold Regularization

Semi-Supervised Learning With GANs: Revisiting Manifold Regularization
Title:
Semi-Supervised Learning With GANs: Revisiting Manifold Regularization
Other Titles:
ICLR 2018
DOI:
Publication Date:
30 April 2018
Citation:
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.
License type:
PublisherCopyrights
Funding Info:
Description:
Accepted to ICLR 2018 Workshop Track
ISBN:

Files uploaded:

File Size Format Action
6c07b1abe56cbdde107de732408f25fc7b652976.pdf 284.86 KB PDF Open