Image compositing is all you need for data augmentation

TL;DR

This paper demonstrates that image compositing significantly improves object detection accuracy and robustness, outperforming other augmentation methods like generative models, especially with limited data.

Contribution

It introduces the effectiveness of image compositing as a data augmentation technique for object detection, showing superior performance over traditional and generative methods.

Findings

Image compositing yields the highest detection performance improvements.

Generative models like Stable Diffusion XL also provide notable gains.

Augmentation enhances model robustness and generalization.

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.