Open access
2026
A Lightweight Single-Token CNN-Transformer Architecture for Robust Multi-Crop Plant Disease Classification
A parameter-efficient hybrid deep learning architecture that combines DenseNet121 with a lightweight Vision Transformer (ViT) module that shows stable convergence behavior, a good precision-recall balance, and effective training behavior with various dataset sizes is presented.
Uswatun Hasanah, Chuan-Ming Liu, Ihsanul Azmi
· IEEE Access · 0 citations