LeafLife: An Explainable Deep Learning Framework with Robustness for Grape Leaf Disease Recognition

TL;DR

This paper presents LeafLife, an explainable deep learning framework for grape leaf disease recognition that combines high accuracy, robustness through adversarial training, and transparency with Grad-CAM, deployed as a user-friendly web app.

Contribution

The study introduces LeafLife, integrating pre-trained models, adversarial training, and Grad-CAM for explainability, specifically tailored for grape leaf disease detection.

Findings

Xception achieved 96.23% accuracy

Adversarial training improved robustness

Grad-CAM provided visual explanations

Abstract

Plant disease diagnosis is essential to farmers' management choices because plant diseases frequently lower crop yield and product quality. For harvests to flourish and agricultural productivity to boost, grape leaf disease detection is important. The plant disease dataset contains grape leaf diseases total of 9,032 images of four classes, among them three classes are leaf diseases, and the other one is healthy leaves. After rigorous pre-processing dataset was split (70% training, 20% validation, 10% testing), and two pre-trained models were deployed: InceptionV3 and Xception. Xception shows a promising result of 96.23% accuracy, which is remarkable than InceptionV3. Adversarial Training is used for robustness, along with more transparency. Grad-CAM is integrated to confirm the leaf disease. Finally deployed a web application using Streamlit with a heatmap visualization and prediction with confidence level for robust grape leaf disease classification.