A dynamic self-attention mechanism for improving deep learning-based plant disease classification

The identification and classification of plant diseases is challenging due to the complexity and variability of symptoms across different species, and the need for timely and accurate diagnosis to effective disease management. However, the existing methods of diagnosing plant diseases often require extensive expert knowledge and can be labor-intensive and time-consuming. This paper presents a novel method leveraging a dynamic self-attention mechanism within convolutional neural networks to enhance the classification accuracy of plant diseases. By allowing the mechanism to focus adaptively on the most informative parts of the input images, this method successfully detects the complex patterns and relationships within the disease symptoms. This method is evaluated by incorporating it in a model that specifically leverages the strengths of EfficientNet architecture combined with the Scaled Exponential Linear Unit (SeLU) activation function on grape leaves dataset containing various types of diseases. This model demonstrates superior performance in detecting a variety of plant diseases, surpassing existing baseline convolutional network methods in both speed and accuracy. This research not only advances the field of plant disease management with cutting-edge AI techniques but also offers a scalable and efficient tool for agriculture practitioners to combat plant diseases more effectively.