Mango Leaf Disease Detection Using Transfer Learning with EfficientNet-B0
TL;DR
This study presents a highly optimized, end-to-end deep learning pipeline leveraging transfer learning via the EfficientNet-B0 architecture for multi-class mango leaf disease classification, establishing a robust and computationally efficient baseline for automated precision pathology.
Abstract
Phytopathological threats to mango (Mangifera indica L.) cultivation cause severe global agricultural yield losses, necessitating rapid and accurate diagnostic frameworks. This study presents a highly optimized, end-to-end deep learning pipeline leveraging transfer learning via the EfficientNet-B0 architecture for multi-class mango leaf disease classification. The model was trained and rigorously evaluated on the MangoLeafBD dataset, comprising 4,000 balanced images across eight categorical states (one healthy control and seven distinct fungal and bacterial pathologies) captured under heterogeneous orchard conditions. Utilizing a stratified 70-15-15 data split, the network achieved exceptional convergence within 16 epochs. Empirical evaluation on an isolated test set of 600 images yielded an absolute classification accuracy of 100 percent, with precision, recall, and F1-scores of 1.0 across all classes and zero off-diagonal misclassifications. Furthermore, the pipeline demonstrated near-zero latency inference on standard edge-computing hardware. These findings validate the deployment viability of lightweight convolutional neural networks in resourceconstrained agricultural environments, establishing a robust and computationally efficient baseline for automated precision pathology.