aiqbench analysis
This research applies an ensemble of pretrained deep learning models combined with adversarial training to achieve high-accuracy classification for lemon leaf diseases, addressing the need for robust agricultural monitoring systems. By leveraging computer vision techniques like Grad-CAM, the study validates model confidence and reliability in noisy data environments without introducing new quantum or foundational AI architectural shifts.
An Ensemble Deep Learning Approach for Reliable and Scalable Lemon Leaf Disease Classification
arXiv:2606.14871v1 Announce Type: cross Abstract: Early detection of plant diseases is crucial to plants and for the farmers. Plant diseases reduce fruit yield and quality, and plants are more susceptible to other stresses when they are infected. The lemon leaf disease dataset contains 1354 images. The dataset has 9 classes. Among the 9 classes only one class is for healthy leaf, and the other 8 classes are leaf diseases. The dataset was split into training (70%), testing (15%) and validation (15%) sets after comprehensive preprocessing. Two pretrained models (InceptionV3 and MobileNetV2) were applied and then combined these models using an ensemble technique to boost robustness. Ensemble models showed a promising performance of 99.27% accuracy. Adversarial Training is applied to improve models' ability and ensure reliable predictions under noisy data. Grad-CAM visualization highlights the important regions of leaf images that validate the model prediction with confidence level.
Abstract:Early detection of plant diseases is crucial to plants and for the farmers. Plant diseases reduce fruit yield and quality, and plants are more susceptible to other stresses when they are infected. The lemon leaf disease dataset contains 1354 images. The dataset has 9 classes. Among the 9 classes only one class is for healthy leaf, and the other 8 classes are leaf diseases. The dataset was split into training (70%), testing (15%) and validation (15%) sets after comprehensive preprocessing. Two pretrained models (InceptionV3 and MobileNetV2) were applied and then combined these models using an ensemble technique to boost robustness. Ensemble models showed a promising performance of 99.27% accuracy. Adversarial Training is applied to improve models' ability and ensure reliable predictions under noisy data. Grad-CAM visualization highlights the important regions of leaf images that validate the model prediction with confidence level.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2606.14871 [cs.CV]
(or arXiv:2606.14871v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.14871 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 241 words
Related coverage
A 3D Pose-Based Ensemble Framework for Cricket Shot Classification and Automated Biomechanical Analysis
arXiv · Sep 24, 2026
TIGER: Time-Series Classification with In-Context-Learning Gated Ensemble of Representations
arXiv · Oct 6, 2026
Hierarchical Specialised Ensembles for Classification of Zebrafish Phenotypes Using the Selected Image Recognition Methods
arXiv · Jul 20, 2026
RCProb: Probabilistic rule extraction from classification tree ensembles
arXiv · Sep 3, 2026