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

• URL: http://arxiv.org/abs/2601.03124v1
• Date: Tue, 06 Jan 2026 15:55:22 GMT
• Title: LeafLife: An Explainable Deep Learning Framework with Robustness for Grape Leaf Disease Recognition
• Authors: B. M. Shahria Alam, Md. Nasim Ahmed,
• Abstract summary: 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.<n>Xception shows a promising result of 96.23% accuracy, which is remarkable than InceptionV3.<n>Finally deployed a web application using Streamlit with a heatmap visualization and prediction with confidence level for robust grape leaf disease classification.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Toward Reliable Tea Leaf Disease Diagnosis Using Deep Learning Model: Enhancing Robustness With Explainable AI and Adversarial Training [0.0]
  This study develops an automated deep learning model for tea leaf disease classification based on the teaLeafBD dataset.<n>The proposed pipeline contains data preprocessing, data splitting, adversarial training, augmentation, model training, evaluation, and comprehension.<n>Our experimental outcomes revealed that EfficientNetB3 achieved the highest classification accuracy of 93%, while DenseNet201 reached 91%.
  arXiv  Detail & Related papers  (2026-02-11T17:21:36Z)
• An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI [0.0]
  The objective of our research is to classify 21 distinct leaf diseases across six plants using deep learning models.<n>VGG19 and Xception achieve the highest accuracies, with 98.90% and 98.66% respectively.
  arXiv  Detail & Related papers  (2025-05-21T21:25:57Z)
• A Novel Feature Extraction Model for the Detection of Plant Disease from Leaf Images in Low Computational Devices [2.1990652930491854]
  The proposed approach integrates various types of Deep Learning techniques to extract robust and discriminative features from leaf images. The dataset contains 10,000 leaf photos from ten classes of tomato illnesses and one class of healthy leaves. AlexNet has an accuracy score of 87%, with the benefit of being quick and lightweight, making it appropriate for use on embedded systems.
  arXiv  Detail & Related papers  (2024-10-01T19:32:45Z)
• PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation [37.383095056084834]
  Plant disease datasets typically lack segmentation labels. Unlike typical datasets that contain images from laboratory settings, PlantSeg primarily comprises in-the-wild plant disease images. PlantSeg is extensive, featuring 11,400 images with disease segmentation masks and an additional 8,000 healthy plant images categorized by plant type.
  arXiv  Detail & Related papers  (2024-09-06T06:11:28Z)
• A Dataset and Benchmark for Shape Completion of Fruits for Agricultural Robotics [30.46518628656399]
  We propose the first publicly available 3D shape completion dataset for agricultural vision systems.<n>We provide an RGB-D dataset for estimating the 3D shape of fruits.
  arXiv  Detail & Related papers  (2024-07-18T09:07:23Z)
• Leafy Spurge Dataset: Real-world Weed Classification Within Aerial Drone Imagery [37.51633459581306]
  Invasive plant species are detrimental to ecology of both agricultural and wildland areas. Invasive plant species such as Euphorbia esula, or leafy spurge, have spread through much of North America from Eastern Europe. We gathered a dataset of leafy spurge presence and absence in grasslands of western Montana, USA, then surveyed these areas with a commercial drone. We trained image classifiers on these data, and our best performing model, a pre-trained DINOv2 vision transformer, identified leafy spurge with 0.84 accuracy.
  arXiv  Detail & Related papers  (2024-05-02T23:53:29Z)
• A Comprehensive Literature Review on Sweet Orange Leaf Diseases [3.0177210416625115]
  Leaf diseases impact fruit quality in the citrus industry. Early detection and diagnosis are necessary for leaf management. This comprehensive review study related to leaf disease compares the performance of the models.
  arXiv  Detail & Related papers  (2023-12-04T09:35:21Z)
• Panoptic Mapping with Fruit Completion and Pose Estimation for Horticultural Robots [33.21287030243106]
  Monitoring plants and fruits at high resolution play a key role in the future of agriculture. Accurate 3D information can pave the way to a diverse number of robotic applications in agriculture ranging from autonomous harvesting to precise yield estimation. We address the problem of jointly estimating complete 3D shapes of fruit and their pose in a 3D multi-resolution map built by a mobile robot.
  arXiv  Detail & Related papers  (2023-03-15T20:41:24Z)
• End-to-end deep learning for directly estimating grape yield from ground-based imagery [53.086864957064876]
  This study demonstrates the application of proximal imaging combined with deep learning for yield estimation in vineyards. Three model architectures were tested: object detection, CNN regression, and transformer models. The study showed the applicability of proximal imaging and deep learning for prediction of grapevine yield on a large scale.
  arXiv  Detail & Related papers  (2022-08-04T01:34:46Z)
• One-Shot Learning with Triplet Loss for Vegetation Classification Tasks [45.82374977939355]
  Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification.
  arXiv  Detail & Related papers  (2020-12-14T10:44:22Z)
• Real-time Plant Health Assessment Via Implementing Cloud-based Scalable Transfer Learning On AWS DeepLens [0.8714677279673736]
  We propose a machine learning approach to detect and classify plant leaf disease. We use scalable transfer learning on AWS SageMaker and importing it on AWS DeepLens for real-time practical usability. Our experiments on extensive image data set of healthy and unhealthy leaves of fruits and vegetables showed an accuracy of 98.78% with a real-time diagnosis of plant leaves diseases.
  arXiv  Detail & Related papers  (2020-09-09T05:23:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.