Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions

Deep learning algorithms have exhibited impressive performance across various computer vision tasks; however, the challenge of overfitting persists, especially when dealing with limited labeled data. This survey explores the mitigation of the overfitting issue through a comprehensive examination of...

Full description

Saved in:
Bibliographic Details
Main Authors: Teerath Kumar, Rob Brennan, Alessandra Mileo, Malika Bendechache
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10699340/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850064907601444864
author Teerath Kumar
Rob Brennan
Alessandra Mileo
Malika Bendechache
author_facet Teerath Kumar
Rob Brennan
Alessandra Mileo
Malika Bendechache
author_sort Teerath Kumar
collection DOAJ
description Deep learning algorithms have exhibited impressive performance across various computer vision tasks; however, the challenge of overfitting persists, especially when dealing with limited labeled data. This survey explores the mitigation of the overfitting issue through a comprehensive examination of image data augmentation techniques, which aim to enhance dataset size and diversity by introducing varied samples. The survey exclusively focuses on these techniques, presenting an insightful overview and introducing a novel taxonomy. The discussion encompasses the strengths and limitations of these techniques. Additionally, the paper provides extensive results evaluating the impact of these techniques on prevalent computer vision tasks: image classification, object detection, and semantic segmentation. The survey concludes with an examination of challenges, limitations, and potential future research directions.
format Article
id doaj-art-90e97573b86148eab3acab3df031ce89
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-90e97573b86148eab3acab3df031ce892025-08-20T02:49:09ZengIEEEIEEE Access2169-35362024-01-011218753618757110.1109/ACCESS.2024.347012210699340Image Data Augmentation Approaches: A Comprehensive Survey and Future DirectionsTeerath Kumar0https://orcid.org/0000-0001-8769-4989Rob Brennan1https://orcid.org/0000-0001-8236-362XAlessandra Mileo2https://orcid.org/0000-0002-6614-6462Malika Bendechache3https://orcid.org/0000-0003-0069-1860CRT-AI and ADAPT Research Centre, School of Computing, Dublin City University, Dublin 9, IrelandADAPT Research Centre, School of Computer Science, University College Dublin, Dublin 4, IrelandINSIGHT and I-Form Research Centre, School of Computing, Dublin City University, Dublin 9, IrelandADAPT and Lero Research Centre, School of Computer Science, University of Galway, Galway, IrelandDeep learning algorithms have exhibited impressive performance across various computer vision tasks; however, the challenge of overfitting persists, especially when dealing with limited labeled data. This survey explores the mitigation of the overfitting issue through a comprehensive examination of image data augmentation techniques, which aim to enhance dataset size and diversity by introducing varied samples. The survey exclusively focuses on these techniques, presenting an insightful overview and introducing a novel taxonomy. The discussion encompasses the strengths and limitations of these techniques. Additionally, the paper provides extensive results evaluating the impact of these techniques on prevalent computer vision tasks: image classification, object detection, and semantic segmentation. The survey concludes with an examination of challenges, limitations, and potential future research directions.https://ieeexplore.ieee.org/document/10699340/Computer visiondata augmentationdeep learningimage classificationobject detectionsegmentation
spellingShingle Teerath Kumar
Rob Brennan
Alessandra Mileo
Malika Bendechache
Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions
IEEE Access
Computer vision
data augmentation
deep learning
image classification
object detection
segmentation
title Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions
title_full Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions
title_fullStr Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions
title_full_unstemmed Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions
title_short Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions
title_sort image data augmentation approaches a comprehensive survey and future directions
topic Computer vision
data augmentation
deep learning
image classification
object detection
segmentation
url https://ieeexplore.ieee.org/document/10699340/
work_keys_str_mv AT teerathkumar imagedataaugmentationapproachesacomprehensivesurveyandfuturedirections
AT robbrennan imagedataaugmentationapproachesacomprehensivesurveyandfuturedirections
AT alessandramileo imagedataaugmentationapproachesacomprehensivesurveyandfuturedirections
AT malikabendechache imagedataaugmentationapproachesacomprehensivesurveyandfuturedirections