Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities

23 Jan 2017Guo-Jun Qi

In this paper, we present the Lipschitz regularization theory and algorithms for a novel Loss-Sensitive Generative Adversarial Network (LS-GAN). Specifically, it trains a loss function to distinguish between real and fake samples by designated margins, while learning a generator alternately to produce realistic samples by minimizing their losses... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Classification CIFAR-10 CLS-GAN Percentage correct 91.7 # 58
Image Classification SVHN CLS-GAN Percentage error 5.98 # 28