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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Comparing data augmentation strategies for deep image classification

McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477 and O'Gara, Sarah (2019) Comparing data augmentation strategies for deep image classification. In: Irish Machine Vision and Image Processing Conference (IMVIP), 28-30 Aug 2019, Dublin, Ireland. ISBN 978-0-9934207-4-0

Abstract
Currently deep learning requires large volumes of training data to fit accurate models. In practice, however, there is often insufficient training data available and augmentation is used to expand the dataset. Historically, only simple forms of augmentation, such as cropping and horizontal flips, were used. More complex augmentation methods have recently been developed, but it is still unclear which techniques are most effective, and at what stage of the learning process they should be introduced. This paper investigates data augmentation strategies for image classification, including the effectiveness of different forms of augmentation, dependency on the number of training examples, and when augmentation should be introduced during training. The most accurate results in all experiments are achieved using random erasing due to its ability to simulate occlusion. As expected, reducing the number of training examples significantly increases the importance of augmentation, but surprisingly the improvements in generalization from augmentation do not appear to be only as a result of augmentation preventing overfitting. Results also indicate a learning curriculum that injects augmentation after the initial learning phase has passed is more effective than the standard practice of using augmentation throughout, and that injection too late also reduces accuracy. We find that careful augmentation can improve accuracy by +2.83% to 95.85% using a ResNet model on CIFAR-10 with more dramatic improvements seen when there are fewer training examples. Source code is available at https://git.io/fjPPy
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Computer vision; deep learning; data augmentation; image classification; supervised learning; CNN; CIFAR-10
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
Published in: Courtney, Jane, Deegan, Catherine and Leamy, Paul, (eds.) IMVIP 2019 Irish Machine Vision & Image Processing Conference proceedings. . Irish Pattern Recognition & Classification Society. ISBN 978-0-9934207-4-0
Publisher:Irish Pattern Recognition & Classification Society
Official URL:http://imvip.ie/2019%20IMVIP%20Proceedings.pdf
Copyright Information:© 2019 The Authors & Irish Pattern Recognition & Classification Society
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland grant number SFI/15/SIRG/3283 and SFI/12/RC/2289.
ID Code:23666
Deposited On:12 Sep 2019 12:30 by Kevin Mcguinness . Last Modified 01 Mar 2022 15:32
Documents

Full text available as:

[thumbnail of IMVIP_2019_Submission.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
310kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record