loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Teerath Kumar 1 ; Alessandra Mileo 2 and Malika Bendechache 3

Affiliations: 1 CRT-AI & ADAPT Research Centre, School of Computing, Dublin City University, Dublin, Ireland ; 2 INSIGHT & I-Form Research Centre, School of Computing, Dublin City University, Dublin, Ireland ; 3 ADAPT & Lero Research Centres, School of Computer Science, University of Galway, Galway, Ireland

Keyword(s): Data Augmentation, Deep Learning, Image Classification, Saliency Augmentation.

Abstract: Improving model generalization in computer vision, especially with noisy or incomplete data, remains a significant challenge. One common solution is image augmentation through occlusion techniques like cutout, random erasing, hide-and-seek, and gridmask. These methods encourage models to focus on less critical information, enhancing robustness. However, they often obscure real objects completely, leading to noisy data or loss of important context, which can cause overfitting. To address these issues, we propose a novel augmentation method, RandSaliencyAug (RSA). RSA identifies salient regions in an image and applies one of six new strategies: Row Slice Erasing, Column Slice Erasing, Row-Column Saliency Erasing, Partial Saliency Erasing, Horizontal Half Saliency Erasing, and Vertical Half Saliency Erasing. RSA is available in two versions: Weighted RSA (W-RSA), which selects policies based on performance, and Non-Weighted RSA (N-RSA), which selects randomly. By preserving contextual i nformation while introducing occlusion, RSA improves model generalization. Experiments on Fashion-MNIST, CIFAR10, CIFAR100, and ImageNet show that W-RSA outperforms existing methods. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 13.58.149.186

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kumar, T., Mileo, A. and Bendechache, M. (2025). RandSaliencyAug: Balancing Saliency-Based Data Augmentation for Enhanced Generalization. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3; ISSN 2184-4321, SciTePress, pages 283-290. DOI: 10.5220/0013098700003912

@conference{visapp25,
author={Teerath Kumar and Alessandra Mileo and Malika Bendechache},
title={RandSaliencyAug: Balancing Saliency-Based Data Augmentation for Enhanced Generalization},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={283-290},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013098700003912},
isbn={978-989-758-728-3},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - RandSaliencyAug: Balancing Saliency-Based Data Augmentation for Enhanced Generalization
SN - 978-989-758-728-3
IS - 2184-4321
AU - Kumar, T.
AU - Mileo, A.
AU - Bendechache, M.
PY - 2025
SP - 283
EP - 290
DO - 10.5220/0013098700003912
PB - SciTePress