Conditional Image Synthesis With Auxiliary Classifier GANs

10/30/2016
by   Augustus Odena, et al.
0

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 classes have samples exhibiting diversity comparable to real ImageNet data.

READ FULL TEXT

page 2

page 4

page 5

page 7

research
04/12/2018

MelanoGANs: High Resolution Skin Lesion Synthesis with GANs

Generative Adversarial Networks (GANs) have been successfully used to sy...
research
03/26/2021

Synthesize-It-Classifier: Learning a Generative Classifier through RecurrentSelf-analysis

In this work, we show the generative capability of an image classifier n...
research
03/20/2022

RareGAN: Generating Samples for Rare Classes

We study the problem of learning generative adversarial networks (GANs) ...
research
10/08/2021

Collaging Class-specific GANs for Semantic Image Synthesis

We propose a new approach for high resolution semantic image synthesis. ...
research
07/17/2018

IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

We present a novel introspective variational autoencoder (IntroVAE) mode...
research
05/27/2021

Deconditional Downscaling with Gaussian Processes

Refining low-resolution (LR) spatial fields with high-resolution (HR) in...
research
12/12/2018

Adversarial Learning of Semantic Relevance in Text to Image Synthesis

We describe a new approach that improves the training of generative adve...

Please sign up or login with your details

Forgot password? Click here to reset