AgroFusionFormer: A Dual-Stage Cross-Attention CNN–Transformer Framework for Robust Plant Disease Detection Across Laboratory and Field Environments
A Dual-Stage Cross-Attention CNN-Transformer framework, called AgroFusionFormer, is proposed for robust plant disease detection to combine EfficientNet-B0 and Swin Transformer by a bidirectional cross-attention mechanism, where the local and global features are refined gradually.