Enhancing weed detection performance by means of GenAI-based image augmentation

TL;DR

This paper demonstrates that using Stable Diffusion for AI-based image augmentation significantly improves weed detection accuracy in deep learning models, especially for edge devices, by generating diverse synthetic training data.

Contribution

It introduces a novel generative AI augmentation method using Stable Diffusion to enhance weed detection datasets, surpassing traditional augmentation techniques.

Findings

Synthetic images improved mAP scores for weed detection models.

Generative augmentation increased dataset diversity and robustness.

Enhanced detection performance on edge devices like YOLO nano.

Abstract

Precise weed management is essential for sustaining crop productivity and ecological balance. Traditional herbicide applications face economic and environmental challenges, emphasizing the need for intelligent weed control systems powered by deep learning. These systems require vast amounts of high-quality training data. The reality of scarcity of well-annotated training data, however, is often addressed through generating more data using data augmentation. Nevertheless, conventional augmentation techniques such as random flipping, color changes, and blurring lack sufficient fidelity and diversity. This paper investigates a generative AI-based augmentation technique that uses the Stable Diffusion model to produce diverse synthetic images that improve the quantity and quality of training datasets for weed detection models. Moreover, this paper explores the impact of these synthetic images on the performance of real-time detection systems, thus focusing on compact CNN-based models such as YOLO nano for edge devices. The experimental results show substantial improvements in mean Average Precision (mAP50 and mAP50-95) scores for YOLO models trained with generative AI-augmented datasets, demonstrating the promising potential of synthetic data to enhance model robustness and accuracy.