Exploring Low-Dimensional Structures in Images Using Deep Fourier Machines

Simple item page
dc.contributor.advisorJiang, Hui
dc.contributor.authorAsadi, Behnam
dc.date.accessioned2023-03-28T21:15:22Z
dc.date.available2023-03-28T21:15:22Z
dc.date.copyright2022-11-11
dc.date.issued2023-03-28
dc.date.updated2023-03-28T21:15:22Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractThe ground-breaking results achieved by Deep Generative Models, when given merely a dataset representing the desired distribution of generated images have caught the interest of scholars. In this work, we introduce a novel structure designed for image generation utilizing the idea behind Fourier Series and Deep Learning function composition. By composing low-dimensional structures, we will first compress a high-dimensional image, and then we will use this latent space to generate fake images. Our compression algorithm gives comparable results to the JPEG algorithm and even, in some cases, outperforms it. Also, our image generation model can generate decent fake images on MNIST and CIFAR-10 datasets and can surpass the first generation of Variational Autoencoders.
dc.identifier.urihttp://hdl.handle.net/10315/40976
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subjectComputer engineering
dc.subjectArtificial intelligence
dc.subject.keywordsMachine learning
dc.subject.keywordsDeep learning
dc.subject.keywordsNeural networks
dc.subject.keywordsImplicit networks
dc.subject.keywordsComputer vision
dc.subject.keywordsImage generation
dc.subject.keywordsImage compression
dc.subject.keywordsGAN
dc.subject.keywordsGenerative networks
dc.subject.keywordsUnsupervised learning
dc.subject.keywordsFourier net
dc.subject.keywordsFourier series
dc.titleExploring Low-Dimensional Structures in Images Using Deep Fourier Machines
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Behnam_Asadi_2022_MSc.pdf
Size:
20.69 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.