Conditional Image Synthesis With Auxiliary Classifier GANs

Augustus Odena, Christopher Olah, Jonathon Shlens

Nov 01, 2016 (modified: Nov 01, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: 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. We construct a variant of GANs employing label conditioning that results in 128x128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 ImageNet classes, 128x128 samples are more than twice as discriminable as artificially resized 32x32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data.
  • TL;DR: We introduce a special GAN architecture that results in high quality 128x128 ImageNet samples; we introduce 2 new quantitative metrics of sample quality.
  • Keywords: Deep learning
  • Conflicts: google.com

Loading