Login | Register

Unsupervised Structure-Consistent Image-to-Image Translation


Unsupervised Structure-Consistent Image-to-Image Translation

Shahfar, Shima (2022) Unsupervised Structure-Consistent Image-to-Image Translation. Masters thesis, Concordia University.

[thumbnail of Shahfar_MCompSc_S2022.pdf]
Text (application/pdf)
Shahfar_MCompSc_S2022.pdf - Accepted Version
Available under License Spectrum Terms of Access.


There have been significant advances in designing deep networks for complex computer vision tasks. One that is of considerable importance is image understanding through pixel-wise classification, i.e. semantic segmentation. Despite the advances, self-supervised algorithms have many limitations and challenges, with perhaps the most significant being generalization. This thesis introduces a method based on generative models as a practical approach for addressing these shortcomings. First, we analyze several semantic segmentation methods to gain insight into their limitations. We investigate the effectiveness of one of the state-of-the-art methods on two different problem settings. The latter part of the thesis introduces an alternative approach using generative adversarial networks and autoencoders for image-to-image translation. The main idea is encoding an image into two latent codes to represent structure and style. We propose a new approach to enforce structure-consistency without requiring semantic labels to disentangle the two latent codes. We further show how this would result in a more detailed style transfer and image manipulation. Finally, we present results on multiple datasets and discuss how our approach can be practical in real-world applications. Our experiments demonstrate that our approach performs better than the baselines -or, in the worst-case, gives comparable results- while solving some of the shortcomings in tasks requiring a semantic mask.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Shahfar, Shima
Institution:Concordia University
Degree Name:M. Comp. Sc.
Program:Computer Science
Date:1 March 2022
Thesis Supervisor(s):Poullis, Charalambos
ID Code:990400
Deposited By: Shima Shahfar
Deposited On:16 Jun 2022 15:11
Last Modified:01 Dec 2023 01:00
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top