11th International Conference on ICTIS

Authors - Darshika Dudhat, Riya Jagani, Sarita Thummar
Abstract - Plant diseases represent one of the major threats for the world's food security and agricultural productivity. In this paper, we present a novel deep CNN model which is improved by the Squeeze-and-Excitation (SE) modules and the Attention Gates (AGs), for multi-class plant disease classification based on five crops including apple, maize, grape, potato, tomato. With large number of image data set and a well-designed training strategy, the established model demonstrates good performance in all aspects including 99% accuracy, 0.99 F1-score and excellent specificity. Exploratory studies are performed through feature visualization and Grad-CAM interpretability. The intense robustness and interpretability of the model give it high potential for practical agricultural applications. The main research methodologies of this paper have: • The proposed Method of Attention-based Deep CNN Model combines (SE) blocks and Attention Gates (AGs), which further improve the channel-wise spatial feature leaning for plant disease classification. • Proposes the Grad-CAM visualizations to show disease-specific regions on leaves and achieves the state-of-the-art performance on five representative crop disease classification tasks. •Introducing attention mechanisms greatly improved the model's ability to focus on disease-related features, as evidenced by its strong generalization performances across a wide array of disease classes.