Enhancing Multi-Class Plant Disease Classification using GAN-Boosted Vision Transformer with XAI Insights

Felicita S A MKavitha B R^*

• Vellore Institute of Technology, Vellore, India

Agriculture is one of the major backbones of the Indian economy, where rice is the most prominent staple crop across the country. However, rice production has been significantly affected due to the occurrence of various plant diseases. This work identifies some of the key diseases and addresses these prominent ones through a state-of-the-art deep learning model. Deep learning and machine learning have emerged as powerful solutions for computer vision based problems. This work proposes a novel multi-class rice leaf disease recognition model named GRG-ViT, which integrates Vision Transformer (ViT), Generative Artificial Intelligence (GenAI), and Explainable Artificial Intelligence (XAI) techniques for better outcomes. The Vision Transformer based framework is designated to capture the long-range spatial dependencies in leaf images which enhances the model's ability to identify the subtle disease patterns. Since the dataset portrayed considerable class imbalance, a GenAI-based synthetic data generation approach is equipped in this model to create balanced training samples which in turn improves the model robustness. This model proposes a hybrid ReLU–GELU based activation mechanism to attain the effective feature representation. The obtained experimental results exhibit that the proposed GRG-ViT model reaches close to an overall accuracy of 96%, which outperforms the conventional approaches. The incorporation of XAI methods like GradCAM, provides both interpretability and transparency by emphasizing the regions impacting model's actions. This research showcases the blended power of ViT, GenAI, and XAI in producing a reliable and high-performing results for rice disease detection in precision agriculture.