[论文] CottonLeafVision: An Explainable and Robust Deep Learning Framework fo...

论文概要

研究领域: CV 作者: Rafi Ahamed, Md. Abir Rahman, Tasnia Tarannum Roza 发布时间: 2026-06-12 arXiv: 2606.14686

中文摘要

在全球范围内，棉花是一种具有高度经济效益的作物，因为纺织业严重依赖它。因此，精确识别和检测棉花叶病对经济稳定至关重要。"CottonLeafVision"的开发目标是准确分类和检测棉花叶病。为实现这一目标，我们在公开可用的棉花叶病图像数据集上评估了多个预训练的深度卷积神经网络，包括DenseNet201、InceptionV3和VGG19。该图像数据集包含七个类别，六个疾病类别和一个健康类别，在各种反映现实世界挑战的田间条件下收集。在这些预训练模型中，使用DenseNet201我们实现了最高的分类准确率98%。为了增强模型的可靠性和可解释性，我们实施了不同的技术和方法，如梯度加权类激活映射（Grad-CAM）、遮挡敏感性分析和对抗训练，以增加模型的噪声抵抗力。最后，我们开发了一个原型，以在真实农业中利用模型的能力。本文展示了深度学习模型在真实棉花疾病管理情境中分类疾病的能力。

原文摘要

Globally, cotton is a highly economically beneficial crop, as the textile industry heavily depends on it. So, the precise identification and detection of cotton leaf disease is crucial for economic stability. The development goal of 'CottonLeafVision' is to accurately classify and detect cotton leaf disease. With this goal, we have evaluated multiple pretrained Deep Convolutional Neural Networks, including DenseNet201, InceptionV3, and VGG19 on a publicly available cotton leaf disease image dataset. This image dataset includes seven classes, six disease classes, and one healthy class, collected under various field conditions reflecting real-world challenges. Among these pretrained models, with DenseNet201, we have achieved the highest classification accuracy of 98%. To enhance the model re...

--- *自动采集于 2026-06-16*

#论文 #arXiv #CV #小凯