Conditional Image Synthesis with Auxiliary Classifier GANs: Difference between revisions
No edit summary |
No edit summary |
||
Line 3: | Line 3: | ||
= Introduction = | = Introduction = | ||
== Motivation == | === Motivation === | ||
== Previous Work == | === Previous Work === | ||
Common methods for image synthesis used today are | Common methods for image synthesis used today are | ||
Line 21: | Line 21: | ||
=== Experimental Results on Image Resolution === | === Experimental Results on Image Resolution === | ||
= Results = | |||
= Critique = | |||
= References = | |||
1. Odena, A., Olah, C., & Shlens, J. (2016). Conditional image synthesis with auxiliary classifier gans. arXiv preprint [http://proceedings.mlr.press/v70/odena17a.html arXiv:1610.09585]. | 1. Odena, A., Olah, C., & Shlens, J. (2016). Conditional image synthesis with auxiliary classifier gans. arXiv preprint [http://proceedings.mlr.press/v70/odena17a.html arXiv:1610.09585]. |
Revision as of 00:09, 6 November 2017
Abstract: "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." Odena et al., 2016
Introduction
Motivation
Previous Work
Common methods for image synthesis used today are
Contributions
Model
The authors propose a conditional GAN that both takes the class to be synthesized as input to the, and includes a classification accuracy term in the loss function of the discriminator.
Measurement Methods
The authors propose two measurement methods to assess the discriminability and diversity of the generated images.
Experimental Results on Image Resolution
Results
Critique
References
1. Odena, A., Olah, C., & Shlens, J. (2016). Conditional image synthesis with auxiliary classifier gans. arXiv preprint arXiv:1610.09585.