cGANs with Multi-Hinge Loss

9 Dec 2019Ilya KavalerovWojciech CzajaRama Chellappa

We propose a new algorithm to incorporate class conditional information into the discriminator of GANs via a multi-class generalization of the commonly used Hinge loss. Our approach is in contrast to most GAN frameworks in that we train a single classifier for K+1 classes with one loss function, instead of a real/fake discriminator, or a discriminator classifier pair... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Conditional Image Generation CIFAR-10 MHingeGAN Inception score 9.58 # 2
FID 7.5 # 3
Conditional Image Generation CIFAR-100 MHingeGAN Inception Score 14.36 # 1
FID 17.3 # 2

Methods used in the Paper