CaneFocus-Net: A Sugarcane Leaf Disease Detection Model Based on Adaptive Receptive Field and Multi-Scale Fusion

In the context of global agricultural modernization, the early and accurate detection of sugarcane leaf diseases is critical for ensuring stable sugar production. However, existing deep learning models still face significant challenges in complex field environments, such as blurred lesion edges, scale variation, and limited generalization capability. To address these issues, this study constructs an efficient recognition model for sugarcane disease detection, named CaneFocus-Net, specifically designed for precise identification of sugarcane leaf diseases. Based on a single-stage detection architecture, the model introduces a lightweight cross-stage feature fusion module (CP) to optimize feature transfer efficiency. It also designs a module combining a channel-spatial adaptive calibration mechanism with multi-scale pooling aggregation to enhance the backbone network's ability to extract multi-scale lesion features. Furthermore, by expanding the high-resolution shallow feature layer to enhance sensitivity toward small-sized targets and adopting a phased adaptive nonlinear optimization strategy, detection and localization accuracy along with convergence efficiency have been further improved. Test results on public datasets demonstrate that this method significantly enhances recognition performance for fuzzy lesions and multi-scale targets while maintaining high inference speed. Compared to the baseline model, precision, recall, and mean average precision (mAP50 and mAP50-95) improved by 1.9%, 4.6%, 1.5%, and 1.4%, respectively, demonstrating strong generalization capabilities and practical application potential. This provides reliable technical support for intelligent monitoring of sugarcane diseases in the field.