Poster
Conditional Image Synthesis with Auxiliary Classifier GANs
Augustus Odena · Christopher Olah · Jon Shlens

Mon Aug 7th 06:30 -- 10:00 PM @ Gallery #59

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 128 × 128 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, 128 × 128 samples are more than twice as discriminable as artificially resized 32×32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data.

Author Information

Augustus Odena (Google Brain)
Christopher Olah (Google Brain)

I want to understand things clearly and explain them well. Research scientist on [Google Brain](http://g.co/brain), co-editor of [Distill](http://distill.pub).

Jon Shlens (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors