Degree Type

Thesis

Date of Award

2020

Degree Name

Master of Science

Department

Computer Science

Major

Computer Science

First Advisor

Ali Jannesari

Abstract

It has been shown that image segmentation models can be improved with an adversarial loss. Additionally, previous analysis of adversarial examples in image classification has shown that image datasets contain features that are not easily recognized by humans. This work investigates the effect of using a second adversarial loss to further improve image segmentation. The proposed model uses two generative adversarial networks stacked together, where the first generator takes an image as input and generates a segmentation map. The second generator then takes this predicted segmentation map as input and predicts the errors relative to the ground truth segmentation map. If these errors contained additional features that are not easily recognized by humans, they could possibly be learned by a discriminator. The proposed model did not consistently show significant improvement over a single generative adversarial model, casting doubt about the existence of such features.

DOI

https://doi.org/10.31274/etd-20200624-162

Copyright Owner

Matthew John Burke

Language

en

File Format

application/pdf

File Size

23 pages

Share

COinS