Tiny-ViT: A Compact Vision Transformer for Efficient and Explainable Potato Leaf Disease Classification

TL;DR

Tiny-ViT is a compact, efficient, and explainable Vision Transformer model designed for accurate potato leaf disease classification in resource-limited settings, outperforming baseline models.

Contribution

Introduces Tiny-ViT, a small and effective Vision Transformer tailored for resource-constrained environments, with high accuracy and interpretability for plant disease detection.

Findings

Achieved 99.85% test accuracy on potato leaf disease dataset.

Outperformed baseline models like DEIT Small, SWIN Tiny, and MobileViT XS.

Demonstrated high reliability with MCC of 0.9990 and low computational costs.

Abstract

Early and precise identification of plant diseases, especially in potato crops is important to ensure the health of the crops and ensure the maximum yield . Potato leaf diseases, such as Early Blight and Late Blight, pose significant challenges to farmers, often resulting in yield losses and increased pesticide use. Traditional methods of detection are not only time-consuming, but are also subject to human error, which is why automated and efficient methods are required. The paper introduces a new method of potato leaf disease classification Tiny-ViT model, which is a small and effective Vision Transformer (ViT) developed to be used in resource-limited systems. The model is tested on a dataset of three classes, namely Early Blight, Late Blight, and Healthy leaves, and the preprocessing procedures include resizing, CLAHE, and Gaussian blur to improve the quality of the image. Tiny-ViT model has an impressive test accuracy of 99.85% and a mean CV accuracy of 99.82% which is better than baseline models such as DEIT Small, SWIN Tiny, and MobileViT XS. In addition to this, the model has a Matthews Correlation Coefficient (MCC) of 0.9990 and narrow confidence intervals (CI) of [0.9980, 0.9995], which indicates high reliability and generalization. The training and testing inference time is competitive, and the model exhibits low computational expenses, thereby, making it applicable in real-time applications. Moreover, interpretability of the model is improved with the help of GRAD-CAM, which identifies diseased areas. Altogether, the proposed Tiny-ViT is a solution with a high level of robustness, efficiency, and explainability to the problem of plant disease classification.