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

Long-term Potentiation01:25

Long-term Potentiation

2.8K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when...
2.8K

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

Comparison of Super-Resolution Deep-Learning Reconstruction and Hybrid Iterative Reconstruction for Coronary Stent Assessment on CTA: A Prospective Multicenter Study.

AJR. American journal of roentgenology·2026
Same author

Effect of smoking on the diagnostic performance of computational fluid dynamics-derived CT-derived fractional flow reserve: a cross-sectional study.

Quantitative imaging in medicine and surgery·2026
Same author

Evolution of pre- and post-operative balance characteristics in patients undergoing anterior cruciate ligament reconstruction: implications for rehabilitation.

Frontiers in bioengineering and biotechnology·2026
Same author

A case report of jejunogastric intussusception complicated by torsion: 17 years after subtotal gastrectomy.

Frontiers in surgery·2026
Same author

Integration of Magnetocardiography and Coronary Computed Tomography Angiography With Machine Learning for Detection of Functionally Significant Myocardial Ischemia.

Reviews in cardiovascular medicine·2026
Same author

Atherosclerotic middle cerebral artery stenosis: adjacent arterial geometry, hemodynamics and plaque features.

Japanese journal of radiology·2026

相关实验视频

Updated: Jul 10, 2025

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

559

激活扩展基于对弱监督语义细分的远程依赖性.

Haipeng Liu1, Yibo Zhao1, Meng Wang1,2

  • 1Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.

PloS one
|November 21, 2023
PubMed
概括

本研究引入了一种新的弱监督语义细分 (WSSS) 方法,该方法使用远程依赖来挖掘语义信息,以提高对象面具的准确性. 这种新的架构增强了伪标签和对象细节,在PASCAL VOC 2012数据集上表现优于现有的方法.

更多相关视频

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

2.8K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

相关实验视频

Last Updated: Jul 10, 2025

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

559
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

2.8K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 人工智能的人工智能

背景情况:

  • 弱监督的语义细分 (WSSS) 通常使用类激活地图 (CAM) 来生成伪标签,但由于注释数据有限,CAM会遭受错误和本地激活.
  • 详细注释的高成本需要高效的WSSS方法来提高细分精度.

研究的目的:

  • 提出一种新的WSSS架构,通过建模远程依赖来扩展对象面具来挖掘语义信息.
  • 为了提高伪标签的可靠性,并改善在细分任务中捕获高级语义细节.

主要方法:

  • 提出了一种新的架构,通过模拟样本内和样本间的远程依赖来挖掘语义信息.
  • 图像被分成块,并应用自我注意力,较少的类别来捕捉远程依赖性,减少错误的预测.
  • 在图像块之间执行全球到本地加权的自我监督对比学习,以将本地CAM激活转移到前景区域.

主要成果:

  • 拟议的模块有效地捕获了优质的语义细节,并产生了更可靠的伪标签.
  • 对PASCAL VOC 2012的实验表明,该模型在验证组中达到76.6%的mIoU,在测试组中达到77.4%的mIoU.
  • 该模型的性能超过了对比基线的性能,表明其在WSSS中的有效性.

结论:

  • 开发的方法通过利用远程依赖和对比学习,成功地解决了WSSS中传统CAM的局限性.
  • 拟议的架构为语义信息挖掘提供了更强大的方法,从而提高了对象口罩生成和细分精度.