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

Enrichment and highly sensitive detection for the chemical agent markers via the rare earth metal ion-modified magnetic nanomaterials.

Talanta·2026

Same author

MSA<sup>2</sup>-Net: Utilizing self-adaptive convolution module to extract multi-scale information in medical image segmentation.

Science progress·2026

Same author

ScaleMamba-YOLO: a multi-scale MambaYOLO for medical object detection.

Scientific reports·2026

Same author

Highly Sensitive and Selective Electrochemical Sensor via Cu-BTC/Au@Cu-BTC Modified Screen-Printed Electrode for the Detection of Chemical Agents.

ACS applied materials & interfaces·2025

Same author

The Development of a Sensitive and Selective Method for the Quantitative Detection of Ricin via ICP-MS Combined with Metal Element Chelated Tag and Modified Nanoparticles.

International journal of molecular sciences·2025

Same author

Experimental Investigation into Dissociation Characteristics of Methane Hydrate in Sediments with Different Contents of Montmorillonite Clay.

Chem & bio engineering·2025

Search research articles

相关实验视频

Updated: Jun 14, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

先进的全球原型细分框架为少数拍摄的高光谱图像分类.

Kunming Xia¹, Guowu Yuan¹, Mengen Xia¹

¹School of Information Science and Engineering, Yunnan University, Kunming 650504, China.

Sensors (Basel, Switzerland)

|August 29, 2024

概括

此摘要是机器生成的。

本研究引入了先进的全球原型细分 (AGPS) 框架,通过捕捉全球上下文并有效利用有限的标记样本来改进高光谱图像 (HSI) 分类.

关键词:

相反的学习 (CL)短时间学习 (FSL)完全卷积网络 (FCN) 是一个完全卷积网络.超光谱图像 (HSI) 分类的分类.

更多相关视频

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Jun 14, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

科学领域:

遥感遥感遥感遥感
计算机视觉计算机视觉
机器学习机器学习

背景情况:

深度学习方法显示出对高光谱图像 (HSI) 分类的希望.
由于基于补丁的输入,现有的HSI分类方法难以捕获全球信息.
有限的标记样品阻碍了当前的HSI分类技术的性能.

研究的目的:

提出一个先进的全球原型细分 (AGPS) 框架,以应对HSI分类中的挑战.
增强全球信息的捕获,并改善在HSI分类中有限的标记样本的利用.

主要方法:

一个基于完全卷积网络 (FCN) 的无补丁特征提取器细分网络 (SegNet) 处理整个HSI.
侧面连接的融合 (FLC) 结构集成了低级和高级特征.
一个Atrous空间金字塔聚合位置注意力 (ASPP-PA) 模块捕获多个尺度的空间信息.
一个先进的全球原型表示学习策略与监督对比学习 (CL) 优化了使用三个约束的网络.

主要成果:

拟议的AGPS框架有效地捕捉了HSI的全球信息.
该方法在使用有限的标记样本时表现出卓越的性能.
三个公共数据集的实验结果表明,AGPS框架的性能优于最先进的方法.

结论:

AGPS框架为HSI分类提供了显著的进步.
全球信息采集和有效样本利用的整合导致了更好的分类准确性.
拟议的方法为具有有限标记数据的HSI分类任务提供了可靠的解决方案.