Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Exploring synthetic Image generation for training computer vision models under data scarcity

Moreu, Enric orcid logoORCID: 0000-0002-0555-3013 (2024) Exploring synthetic Image generation for training computer vision models under data scarcity. PhD thesis, Dublin City University.

This thesis presents research conducted in the area of synthetic data generation for computer vision tasks. The research aims to address the challenge of datahungry deep learning models by generating synthetic images that can effectively train computer vision models to solve tasks such as object counting, polyp segmentation, and pattern classification. The work carried out explores the use of various techniques to ensure effective use of synthetic data, including domain randomisation and domain adaptation in both self- and semi-supervised setups. Through the application of these techniques, the research aims to develop a robust and effective approach for generating synthetic data that can improve the performance of computer vision models with a reduced amount of human annotations.
Item Type:Thesis (PhD)
Date of Award:March 2024
Supervisor(s):O'Connor, Noel E. and McGuinness, Kevin
Subjects:Computer Science > Artificial intelligence
Computer Science > Image processing
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Institutes and Centres > INSIGHT Centre for Data Analytics
Research Institutes and Centres > FUJO. Institute for Future Media, Democracy and Society
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 License. View License
Funders:European Commission
ID Code:29380
Deposited On:22 Mar 2024 13:44 by Noel Edward O'connor . Last Modified 22 Mar 2024 13:44

Full text available as:

[thumbnail of PhD_Thesis_Enric_Moreu_2024.pdf]
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0


Downloads per month over past year

Archive Staff Only: edit this record