Conditional Image Synthesis With Auxiliary Classifier GANs

ICML 2017 Augustus OdenaChristopher OlahJonathon Shlens

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Conditional Image Generation CIFAR-10 AC-GAN Inception score 8.25 # 5
Conditional Image Generation ImageNet 128x128 AC-GAN Inception score 28.5 # 6