Three ploys for robust co-generation with generative adversarial nets

Generative adversarial nets (GANs) and variational auto-encoders enable accurate modeling of high-dimensional data distributions by forward propagating a sample drawn from a latent space. However, an often overlooked shortcoming is their inability to find an arbitrary marginal distribution, which is useful for completion of missing data in tasks like super-resolution, image inpainting, etc., where we don’t know the missing part ahead of time. To address such applications it seems intuitive at first to search for that latent space sample which ‘best’ matches the observations. However, irrespective of the GAN loss, unexpected challenges arise: we find that the energy landscape of well trained generators is extremely hard to optimize, exhibiting ‘folds’ that are very hard to overcome. To address this issue, in this thesis, three ploys are proposed which help to address the challenge for all investigated GAN losses and which yield more accurate reconstructions, quantitatively and qualitatively.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2019

Author dc:creator

• Kothapalli, Krishna Harsha Reddy

Contributors dc:contributor

• Schwing, Alexander

• Deep Learning
• Machine Learning
• GAN
• Cogeneration

Statement dc:rights

• Copyright 2019 Krishna Harsha Reddy Kothapalli

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/104903

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/104903