Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Classification of Systems-II01:31

Classification of Systems-II

651
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
651

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

Sequential surgery following conversion therapy based on combination of immune checkpoint inhibitors and antiangiogenic targeted drugs as a potential approach for advanced hepatocellular carcinoma with portal vein tumor thrombus: a prospective study.

Journal of gastrointestinal oncology·2026
Same author

A novel ABCD1 frameshift mutation detected in a Chinese male with adrenomyeloneuropathy.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2026
Same author

Pore size-regulated MOF nanozyme-based colorimetric sensor array for rapid detection and classification of mycotoxins.

Biosensors & bioelectronics·2026
Same author

OmpU elicits cross-protective bactericidal activity against Vibrio species: a surface-exposed antigen with vaccine potential.

Journal of applied microbiology·2026
Same author

Surgical treatment and prognosis of type II congenital extrahepatic portosystemic shunts: A single-center experience of 31 cases.

Intractable & rare diseases research·2026
Same author

Heterogeneity of Cancer-Associated Fibroblasts and Precision Targeting Strategies for Cancer Therapy.

Thoracic cancer·2026

相关实验视频

Updated: May 6, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.4K

一个代的伪标签生成框架,用于半监督的高光谱图像分类,使用分段任何模型.

Zheng Zhao1, Guangyao Zhou2, Qixiong Wang1

  • 1School of Astronautics, Beihang University, Beijing, China.

Frontiers in plant science
|January 7, 2025
PubMed
概括

本研究介绍了一种代伪标签生成 (IPG) 框架,使用分段任何模型 (SAM) 来改进半监督的超光谱图像分类. 该方法通过从有限的数据生成可靠的伪标签来提高分类准确性.

关键词:
分段 任何 模型 模型超光谱图像分类的分类方法伪标签的生成 伪标签的生成远程传感是一种遥感技术.半监督学习 半监督学习

更多相关视频

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.6K

相关实验视频

Last Updated: May 6, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.4K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.6K

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:

  • 超光谱图像分类面临的挑战是有限的注释数据.
  • 半监督学习提供解决方案,但依赖于高质量的伪标签.
  • 伪标签质量至关重要,尤其是在培训的早期.

研究的目的:

  • 为半监督的超光谱图像分类提出一个代伪标签生成 (IPG) 框架.
  • 为了利用分段任何模型 (SAM) 的结构性先前信息.
  • 通过生成可靠的伪标签来提高分类性能.

主要方法:

  • 使用一小组注释标签作为SAM点提示,用于初始细分面具.
  • 引入了一种光谱投票策略,以统一跨光谱带的细分口罩.
  • 开发了一个空间信息一致性驱动的损失函数,用于自适应性伪标签选择.
  • 采用了伪标签的代改进作为SAM提示.

主要成果:

  • 实际上,IPG框架为培训提供了可靠的伪标签.
  • 用IPG生成的标签进行训练的简单的2D CNN显著超过了最先进的方法.
  • 在印度松树和帕维亚大学数据集上表现得更好.

结论:

  • 拟议的IPG框架成功地解决了在超光谱图像分类中有限的注释数据的挑战.
  • 通过SAM利用结构先验显著提高了半监督学习的表现.
  • 该方法提供了一个强大的方法来丰富培训数据并提高分类准确性.