相关实验视频

Updated: Mar 14, 2026

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

基于比较概念的可解释作物害虫和疾病识别树木

Bingjing Jia¹, Zhiwei Zheng¹, Jinyu Zeng¹

¹Anhui Science and Technology University, Bengbu, China.

|March 12, 2026

概括

本研究介绍了对比原型树 (CPTR),这是一个可解释的深度学习模型,用于作物害虫和疾病的识别. 通过透明的决策,CPTR提高了识别准确性和用户信任,改善了农业应用.

科学领域:

农业科学农业科学
计算机科学计算机科学
人工智能的人工智能

背景情况:

深度学习模型在农作物害虫和疾病识别方面提供了高准确性和效率,但往往缺乏可解释性,阻碍了用户的信任和在农业中的采用.
提高这些模型的透明度和可解释性对于它们在农业生产中的广泛应用至关重要.

研究的目的:

提出一种新的可解释的深度学习模型,用于作物害虫和疾病的识别.
通过提供对识别结果的直观解释,增强模型透明度并建立用户信任.

主要方法:

开发了对比原型树 (CPTR) 模型,整合了概念原型和决策树结构,以明确匹配路径.
利用SimCLR对比学习框架来改善深度图像特征的学习,提高识别性能.

主要成果:

在AppleLeaf9上,CPTR获得了83.74%的高精度,在Cassava上达到94.80%,在Cashew数据集上达到96.01%.
在评估的数据集中,与标准原型树模型相比,准确性得到了4.12%,0.34%和0.51%的改进.

结论:

拟议的CPTR模型有效地平衡了分类能力和可解释性,为其预测提供了直观的解释.
在多个数据集中,CPTR显示出卓越的性能和有效性,突出了其在农业害虫和疾病识别中实际使用的潜力.

更多相关视频

Evaluating Dryocosmus Kuriphilus-induced Damage on Castanea Sativa

Evaluating Dryocosmus Kuriphilus-induced Damage on Castanea Sativa

Published on: August 30, 2018

A Contrast of Three Inoculation Techniques used to Determine the Race of Unknown Fusarium oxysporum f.sp. niveum Isolates

A Contrast of Three Inoculation Techniques used to Determine the Race of Unknown Fusarium oxysporum f.sp. niveum Isolates

Published on: October 28, 2021

相关概念视频

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.