Spectral Normalization for Generative Adversarial Networks

One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator... (read more)

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Generation CIFAR-10 SN-GANs Inception score 8.22 # 22
FID 21.7 # 30
Image Generation STL-10 SN-GAN FID 40.1 # 6
Inception score 9.10 # 5

Methods used in the Paper