Barros Arantes, Renato (2023). Automatic Learning of Augmentation Strategies Based on Deep Learning Generative Models. PHD thesis, Aston University.
Abstract
The limited quantity of training data can hamper supervised machine learning methods that generally need large amounts of data to avoid overfitting. Data augmentation has a long history of using machine learning algorithms and is a straightforward method to overcome overfitting and improve model generalisation. However, data augmentation schemes are typically designed by hand and demand substantial domain knowledge to create suitable data transformations. This dissertation introduces a new deep learning Generative Adversarial Network (GAN) method for image synthesis that automatically learns an augmentation strategy appropriate for sparse datasets and can be used to improve pixel-level semantic segmentation accuracy by filling the gaps in the training set. The contributions of this thesis are summarised as follows. (1) Initially, in the image synthesis domain, we propose two new generative methods based on GAN that can synthesise arbitrary-sized, high resolution images based on a single source image. (2) Next, for the first time, by using a loss function constrained by semantic segmentation, we introduce a new GAN-based model that does label-to-image translation and delivers state-of-the-art results as an augmentation strategy. (3) Additionally, this thesis presents the first strong evidence that data density correlates with the improvement brought about by an augmentation algorithm based on GAN.
Additional Information: | Copyright © Renato Barros Arantes, 2023. Renato Barros Arantes asserts their moral right to be identified as the author of this thesis. This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that its copyright rests with its author and that no quotation from the thesis and no information derived from it may be published without appropriate permission or acknowledgement. If you have discovered material in Aston Publications Explorer which is unlawful e.g. breaches copyright, (either yours or that of a third party) or any other law, including but not limited to those relating to patent, trademark, confidentiality, data protection, obscenity, defamation, libel, then please read our Takedown Policy and contact the service immediately. |
---|---|
Institution: | Aston University |
Uncontrolled Keywords: | GAN,Data augmentation,Semantic segmentation |
Last Modified: | 28 Jun 2024 08:23 |
Date Deposited: | 09 Feb 2024 11:45 |
Completed Date: | 2023 |
Authors: |
Barros Arantes, Renato
|