Conditional Image Synthesis with Auxiliary Classifier GANs
Conditional Image Synthesis with Auxiliary Classifier GANsAugustus Odena1Christopher Olah1Jonathon Shlens1AbstractIn this paper we introduce new methods for theimproved training of generative adversarial net-works (GANs) for Image Synthesis . We con-struct a variant of GANs employing label condi-tioning that results in128 128resolution im-age samples exhibiting global coherence. Weexpand on previous work for Image quality as-sessment to provide two new analyses for assess-ing the discriminability and diversity of samplesfrom class- Conditional Image Synthesis analyses demonstrate that high resolutionsamples provide class information not present inlow resolution samples. Across 1000 ImageNetclasses,128 128samples are more than twiceas discriminable as artificially resized32 32samples.
several ad-hoc measures for image sample discriminabil-ity and diversity. Our hope is that this work might provide quantitative measures that may be used to aid training and subsequent development of image synthesis models. 4.1. Generating High Resolution Images Improves Discriminability Building a class-conditional image synthesis model neces-
Download Conditional Image Synthesis with Auxiliary Classifier GANs
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: