Interpretable Plant Leaf Disease Detection Using Attention-Enhanced CNN
Balram Singh, Ram Prakash Sharma, Somnath Dey
TL;DR
This work introduces CBAM-VGG16, an interpretable CNN for plant leaf disease detection that embeds Convolution Block Attention Modules after every convolutional stage to boost localization and transparency. Through evaluation on five diverse datasets, the model achieves state-of-the-art accuracy (up to 98.87%) and robust explainability via CBAM attention maps, Grad-CAM/Grad-CAM++, and Layer-wise Relevance Propagation. The authors provide comprehensive qualitative and quantitative analyses, including t-SNE and UMAP visualizations, to demonstrate improved feature discriminability. The approach advances explainable AI in agricultural diagnostics and offers a reliable, transparent tool for smart farming with publicly available code.
Abstract
Plant diseases pose a significant threat to global food security, necessitating accurate and interpretable disease detection methods. This study introduces an interpretable attention-guided Convolutional Neural Network (CNN), CBAM-VGG16, for plant leaf disease detection. By integrating Convolution Block Attention Module (CBAM) at each convolutional stage, the model enhances feature extraction and disease localization. Trained on five diverse plant disease datasets, our approach outperforms recent techniques, achieving high accuracy (up to 98.87%) and demonstrating robust generalization. Here, we show the effectiveness of our method through comprehensive evaluation and interpretability analysis using CBAM attention maps, Grad-CAM, Grad-CAM++, and Layer-wise Relevance Propagation (LRP). This study advances the application of explainable AI in agricultural diagnostics, offering a transparent and reliable system for smart farming. The code of our proposed work is available at https://github.com/BS0111/PlantAttentionCBAM.