What question did this study set out to answer?

Examine the effectiveness of various deep learning architectures in classifying leaf diseases with a focus on explainability.

Explainable Deep Learning for Plant Leaf Diseases: A Comparative Study of Grad CAM

View Full Paper

Ask AI

Bookmark

Authors

Comparative trial evaluates explainable deep learning models for leaf disease detection, suggesting essential tools for agricultural practices.

Examine the effectiveness of various deep learning architectures in classifying leaf diseases with a focus on explainability.
Compared three convolutional neural networks: ConvNeXt-Tiny, MobileNetV2, and VGG16.
Utilized Gradient-weighted Class Activation Mapping (Grad-CAM) for explainable visualizations.
Assessed model accuracy on potato, maize, and pepper leaf diseases.
ConvNeXt-Tiny achieved 99-100% accuracy across all plants.
MobileNetV2 attained 97-100% accuracy with reduced computational costs.
VGG16 recorded 97-99.5% accuracy, with misclassifications mostly due to shadows and natural patterns.

Gökten et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Comparative trial evaluates explainable deep learning models for leaf disease detection, suggesting essential tools for agricultural practices.

Examine the effectiveness of various deep learning architectures in classifying leaf diseases with a focus on explainability.
Compared three convolutional neural networks: ConvNeXt-Tiny, MobileNetV2, and VGG16.
Utilized Gradient-weighted Class Activation Mapping (Grad-CAM) for explainable visualizations.
Assessed model accuracy on potato, maize, and pepper leaf diseases.
ConvNeXt-Tiny achieved 99-100% accuracy across all plants.
MobileNetV2 attained 97-100% accuracy with reduced computational costs.
VGG16 recorded 97-99.5% accuracy, with misclassifications mostly due to shadows and natural patterns.

Gökten et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark