Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Programmable macrophage interface engineering enables targeted antibacterial therapy in immunosuppressed infections.

Science bulletin·2026

Same author

Clinical nurses as digital guardians: unlocking the key determinants of digital resilience in the AI era.

Frontiers in public health·2026

Same author

How organizational support promotes teacher professional recognition: a perspective on teachers' autonomous learning and teaching abilities.

Frontiers in psychology·2026

Same author

Metabolic vulnerability index and Life's Essential 8 with risk of major adverse cardiovascular events.

NPJ cardiovascular health·2026

Same author

How does teacher support impact the academic achievement of boarding junior high school students? The mediating role of academic self-concept and the moderating effect of academic anxiety.

Frontiers in psychology·2026

Same author

Characterization of the intrahepatic microbiome in patients with HBV-related end-stage liver disease.

Virulence·2026

Search research articles

相关实验视频

Updated: Jun 10, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

基于语网络的植物病的弱监督局部化模型.

Jiyang Chen¹, Jianwen Guo¹, Hewei Zhang¹

¹Dongguan University of Technology, Dongguan, China.

Frontiers in plant science

|October 14, 2024

概括

这项研究介绍了罗神经网络模型用于农业疾病局部化. 农业疾病精确定位类激活映射 (ADPL-CAM) 算法准确地识别了病变的植物区域,提高了检测准确度和减少了错误警报.

科学领域:

农业科学农业科学
计算机视觉计算机视觉
机器学习机器学习

背景情况:

植物疾病对作物产量和农业生产率构成重大威胁.
目前的基于图像的疾病检测方法与症状变异性作斗争,导致高错误报警率.

研究的目的:

开发一个高效,弱监督的模型,用于精确地定位农业疾病.
提高植物疾病检测系统的准确性和减少错误警报.

主要方法:

利用一个带有重量共享机制的罗神经网络来捕捉患病植物的视觉差异.
开发并集成了农业疾病精确定位类激活映射 (ADPL-CAM) 算法,用于准确的定位.
评估了该模型在各种网络架构上的性能,包括ResNet50和SPDNet.

主要成果:

与GradCAM和SmoothCAM相比,ADPL-CAM在所有测试的网络架构中表现出卓越的性能.
在ResNet50上实现了3.96%更高的top-1准确度和27.09%更高的平均交叉点在Union (IoU) 超过GradCAM.
在SPDNet架构上,ADPL-CAM达到54.29%的top-1精度和67.5%的平均IOU,优于其他方法.

结论:

关键词:

姆人的网络.类激活映射类的映射.深度学习是一种深度学习.植物疾病植物疾病弱监督的本地化本地化.

更多相关视频

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

Published on: May 17, 2020

相关实验视频

Last Updated: Jun 10, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

Published on: May 17, 2020

与ADPL-CAM一起开发的语网络模型有效地局部化了植物疾病.
拟议的方法提供了疾病植物叶子的准确和快速识别和定位.
这种方法有可能显著提高农业的疾病管理策略.