A robust cross-crop disease detection framework based on SIS-YOLOv11 with climate-adaptive mechanisms.

Abstract

Plant disease detection under complex climatic conditions and cross-crop scenarios remains a critical challenge. To address this, we propose a novel SimAM-Inception-StyleRandomization (SIS)-YOLOv11 algorithm based on YOLOv11n for early/late blight detection on potato and tomato leaves. Our core innovations are: 1) A C3k2-SSI module integrating Style Randomization, Inception architecture, and SimAM attention to enhance cross-crop generalization; 2) A Fusion-InceptionConv module for fine-grained feature extraction under rainfall/haze noise; 3) SPPF-Inception and C2PSA-IS modules to optimize multi-scale feature fusion; 4) DepGraph pruning to reduce 47.82% parameters while improving performance. Experiments show that the pruned SIS-YOLOv11 outperforms YOLOv11n by 3.7% in precision, 6.6% in recall, 5.4% in mAP50, and 7.9% in mAP50-95, and surpasses mainstream models (Faster R-CNN, SSD, etc.). This study provides a robust, lightweight solution for automated cross-crop disease detection in complex agricultural environments.