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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Visual representation learning with deep neural networks under label and budget constraints

Arazo Sánchez, Eric (2022) Visual representation learning with deep neural networks under label and budget constraints. PhD thesis, Dublin City University.

Abstract
This thesis presents the work done in the area of semi-supervised learning, label noise, and budgeted training for deep learning approaches to computer vision. The improvements seen in computer vision since the successful introduction of deep learning rely on the availability of large amounts of labeled data and long lasting training processes. First, this research studies the three main alternatives to fully supervised deep learning categorized in three different levels of supervision: unsupervised learning (no label involved), semi-supervised learning (a small set of labeled data is available), and label noise (all the samples are labeled but some of them are incorrect). These alternatives aim at reducing the cost of building fully annotated and finely curated datasets, which in most cases is time consuming and requires expert annotators. State-of-the-art performance has been achieved in several semi-supervised, unsupervised, and label noise benchmarks including CIFAR10, CIFAR100, and STL-10. Additionally, the solutions proposed for learning in the presence of label noise have been validated in realistic benchmarks built with datasets annotated from web information: WebVision and Clothing1M. Second, this research explores alternatives to reduce the computational cost of the training of deep learning systems that currently require hours or days to reach state-of-the-art performance. Particularly, this research studied budgeted training, i.e.~when the training process is limited to a fixed number of iterations. Experiments in this setup showed that for better model convergence, variety in the data is preferable than the importance of the samples used during training. As a result of this research, three main author publications have been generated, one more has been recently submitted to review for a conference, and several other secondary author publications have been produced in close collaboration with other researchers in the centre.
Metadata
Item Type:Thesis (PhD)
Date of Award:February 2022
Refereed:No
Supervisor(s):McGuinness, Kevin and O'Connor, Noel E.
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 Initiatives and Centres > INSIGHT Centre for Data Analytics
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 3.0 License. View License
Funders:Science Foundation Ireland
ID Code:26541
Deposited On:15 Feb 2022 12:47 by Kevin Mcguinness . Last Modified 15 Feb 2022 12:47
Documents

Full text available as:

[thumbnail of Eric_Arazo_PhD_Thesis_2022.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0
45MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record