GAF-Net: An Enhanced Multidisease for Corn Leaves Detection Model Based on YOLOv8

Corn leaf pest and disease detection techniques play a vital role in enabling precise pesticide application and optimizing disease management strategies. However, traditional machine learning methods require manual feature design and exhibit limited generalization capabilities. While early deep learning models improved automation, they struggled to handle the complexity of diverse pest and disease features effectively. ​The primary objective of this study is to address these limitations by developing a novel detection model, Gsconv-Adaptive Feature Fusion Network (GAF-Net), which enhances the accuracy and robustness of corn pest and disease detection. Built upon YOLOv8, GAF-Net incorporates the adaptive spatial feature fusion strategy and the Grouped Spatial Convolution (GSConv) module, which significantly improve multiscale spot feature integration and effective processing of damaged leaf regions. ​This innovation enables GAF-Net to achieve superior performance in complex agricultural environments. To overcome the scarcity of high-quality datasets, we constructed an integrated image dataset encompassing four major pest and disease features: Northern corn leaf blight, pest damage, brown spot, and downy mildew. Experimental results demonstrate that GAF-Net achieves outstanding performance, with a mean average precision (mAP)_50 score of 80.8% (a 4.1% improvement over the baseline model) and an mAP (50–95) score of 52.6% (a 3.3% enhancement). These quantified results highlight the efficacy of GAF-Net in addressing the challenges of corn pest and disease detection, making it a valuable tool for precision agriculture.