Improving Generative Adversarial Networks with Image Quality Assessment
AuthorPerkins-Ollila, Justin W.
AdvisorZhang, Hao H.
MetadataShow full item record
PublisherThe University of Arizona.
RightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction, presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
AbstractThe research to find new ways to improve Generative Adversarial Networks (GANs) and ways to evaluate the data they produce is quite active. However, approaches to directly using those evaluation steps to improve Generative Adversarial Networks are quite sparse. I propose a modification to the correction step of the stochastic gradient descent algorithm for the generator of a Generative Adversarial Net using the Structural Image Similarity Measure in order to increase the efficiency of a Generative Adversarial Network.
Degree ProgramGraduate College