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

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

From Experiment-Driven to Theory- and Data-Driven: A Computational Paradigm Shift in High-Entropy Electrocatalyst Design.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Machine learning-based prediction of difficult laryngoscopy in infants with Pierre Robin sequence using quantitative 3D computed tomography parameters.

Frontiers in neurology·2026
Same author

Comparative effectiveness of regional analgesia techniques after gastrectomy for gastric cancer: a systematic review and network meta-analysis of randomized trials.

Frontiers in medicine·2026
Same author

B7 homolog 3-targeted CAR-T cells secreting EGFR T-cell engagers for improved control of glioblastoma progression.

Molecular biomedicine·2026
Same author

Clinic-based characteristics of animal-related injury presentations in Hangzhou, China: a 10-year retrospective analysis.

Frontiers in public health·2026
Same author

A macrophage-targeted bivalent saRNA vaccine protects against ocular and cutaneous HSV-1 infection in mice.

Journal of controlled release : official journal of the Controlled Release Society·2026

相关实验视频

Updated: Jun 2, 2025

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

2.7K

一个半监督的边界细分网络用于遥感图像.

Yongdong Chen1, Zaichun Yang2, Liangji Zhang2

  • 1Shaoxing University Yuanpei College, Shaoxing, 312000, China. chenyd@usx.edu.cn.

Scientific reports
|January 15, 2025
PubMed
概括

本研究引入了一种半监督边界细分网络 (BS-GAN) 用于遥感图像. 通过使用混合注意力和边界门模块,BS-GAN提高了准确性,减少了对标记数据的需求.

科学领域:

  • 计算机视觉 计算机视觉
  • 遥感 遥感 遥感 遥感
  • 机器学习 机器学习

背景情况:

  • 由于物体尺寸和界限不清楚,远程传感图像的准确细分是很困难的.
  • 现有的方法往往需要大量的标记数据,这限制了它们的实际应用.

研究的目的:

  • 开发一种新的半监督边界分段网络 (BS-GAN),用于改进远程传感图像分析.
  • 提高细分精度,减少对标记数据集的依赖.

主要方法:

  • 提出了一种半监督学习方法,以尽量减少对注释数据的需求.
  • 引入了一种新的混合注意力 (MA) 机制,用于聚合远程上下文信息.
  • 开发了一个边界门模块 (BGM),利用多任务学习来改进边界.

主要成果:

  • 在三个基准数据集上,BS-GAN表现出卓越的细分精度.
  • 与现有方法相比,该网络展示了增强的概括能力.
  • 混合注意力和边界门模块有效地改善了边界划分.

结论:

  • 拟议的BS-GAN有效地解决了遥感图像细分方面的挑战.

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

366

相关实验视频

Last Updated: Jun 2, 2025

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

2.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

366
  • 半监督学习与先进的注意力和门机制相结合,为图像细分提供了一个有希望的方向.
  • BS-GAN为遥感应用提供了更准确和更有效的数据解决方案.