Accurate and real-time detection of maize foliar diseases is important for field disease monitoring and yield protection. However, in complex natural field environments, different diseases often exhibit high visual similarity, and early weak lesions are easily confused with background elements such as dry leaves, soil, and shadows, leading to false positives and missed detections in existing models. To address these challenges, this study proposes an improved lightweight maize foliar disease detection model based on YOLO11, termed CKM-YOLO11. First, a mixed local channel attention mechanism is introduced and adapted to the task in the backbone to construct the C3k2-MLCA module, thereby enhancing joint modeling of local lesion textures, edge details, and global contextual information. Second, a lightweight residual attention module, named MLCA-HeadLite, is designed at the P5 layer of the neck/head to alleviate the suppression of weak lesion responses during deep feature fusion. Experimental results demonstrate that the proposed model achieves an mAP@50 of 81.5% on a self-constructed maize disease dataset with complex field backgrounds, improving mAP@50 and mAP@50–95 by 3.2 and 3.4 percentage points, respectively, compared with the baseline YOLO11, while maintaining a low parameter count and computational cost. Further analyses based on the confusion matrix, comparisons of detection results, and Grad-CAM visualizations indicate that the proposed model performs better in background suppression, retention of weak lesion responses, and robustness in complex scenes. This study provides a reference for the lightweight design of maize foliar disease detection models in complex field environments and their deployment on agricultural edge devices.
Zhu et al. (Fri,) studied this question.