Generative AI-based Pipeline Architecture for Increasing Training Efficiency in Intelligent Weed Control Systems
This addresses the challenge of data scarcity in agricultural AI applications, offering a method to enhance training efficiency and performance for weed control systems, though it is incremental as it builds on existing models like SAM and Stable Diffusion.
The study tackled the problem of limited and costly datasets for deep learning in intelligent weed control by generating synthetic images using a GenAI-based pipeline, resulting in YOLO models trained with 10% synthetic and 90% real images achieving superior mAP50 and mAP50-95 scores compared to those trained solely on real images.
In automated crop protection tasks such as weed control, disease diagnosis, and pest monitoring, deep learning has demonstrated significant potential. However, these advanced models rely heavily on high-quality, diverse datasets, often limited and costly in agricultural settings. Traditional data augmentation can increase dataset volume but usually lacks the real-world variability needed for robust training. This study presents a new approach for generating synthetic images to improve deep learning-based object detection models for intelligent weed control. Our GenAI-based image generation pipeline integrates the Segment Anything Model (SAM) for zero-shot domain adaptation with a text-to-image Stable Diffusion Model, enabling the creation of synthetic images that capture diverse real-world conditions. We evaluate these synthetic datasets using lightweight YOLO models, measuring data efficiency with mAP50 and mAP50-95 scores across varying proportions of real and synthetic data. Notably, YOLO models trained on datasets with 10% synthetic and 90% real images generally demonstrate superior mAP50 and mAP50-95 scores compared to those trained solely on real images. This approach not only reduces dependence on extensive real-world datasets but also enhances predictive performance. The integration of this approach opens opportunities for achieving continual self-improvement of perception modules in intelligent technical systems.