Image Compositing Is all You Need for Data Augmentation

Ang Jia Ning Shermaine, Michalis Lazarou, Tania Stathaki

2025

Abstract

This paper investigates the impact of various data augmentation techniques on the performance of object detection models. Specifically, we explore classical augmentation methods, image compositing, and advanced generative models such as Stable Diffusion XL and ControlNet. The objective of this work is to enhance model robustness and improve detection accuracy, particularly when working with limited annotated data. Using YOLOv8, we fine-tune the model on a custom dataset consisting of commercial and military aircraft, applying different augmentation strategies. Our experiments show that image compositing offers the highest improvement in detection performance, as measured by precision, recall, and mean Average Precision (mAP@0.50). Other methods, including Stable Diffusion XL and ControlNet, also demonstrate significant gains, highlighting the potential of advanced data augmentation techniques for object detection tasks. The results underline the importance of dataset diversity and augmentation in achieving better generalization and performance in real-world applications. Future work will explore the integration of semi-supervised learning methods and further optimizations to enhance model performance across larger and more complex datasets.

Paper Citation

in Harvard Style

Shermaine A., Lazarou M. and Stathaki T. (2025). Image Compositing Is all You Need for Data Augmentation. 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, SciTePress, pages 789-796. DOI: 10.5220/0013370300003912

in Bibtex Style

@conference{visapp25,
author={Ang Shermaine and Michalis Lazarou and Tania Stathaki},
title={Image Compositing Is all You Need for Data Augmentation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={789-796},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013370300003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Image Compositing Is all You Need for Data Augmentation
SN - 978-989-758-728-3
AU - Shermaine A.
AU - Lazarou M.
AU - Stathaki T.
PY - 2025
SP - 789
EP - 796
DO - 10.5220/0013370300003912
PB - SciTePress