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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

6.8K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
6.8K

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

Essential minerals and risk of pancreatic diseases: a large-scale prospective cohort study.

Frontiers in nutrition·2026
Same author

Targeting HAS2 to enhance anti-tumor immunity in pancreatic cancer via PD-L1 regulation.

Communications biology·2026
Same author

Nuclear prostaglandin E synthase 3 promotes hepatocellular carcinoma growth with immunosuppressive macrophage polarization via the SP1/TGF-β axis.

Molecular biomedicine·2026
Same author

Real-world safety profile and mechanistic insights into regorafenib-induced liver failure: a pharmacovigilance study integrated with network toxicology.

Frontiers in pharmacology·2026
Same author

Neural Stimulation of Prefrontal Cortex Improves Food-Related Memory Suppression.

Obesity (Silver Spring, Md.)·2025
Same author

Few-shot event-based action recognition.

Neural networks : the official journal of the International Neural Network Society·2025

相关实验视频

Updated: May 24, 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

451

通过多颗粒度信心对齐来完善伪标签,用于无监督的跨域对象检测.

Jiangming Chen, Li Liu, Wanxia Deng

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
    |March 3, 2025
    PubMed
    概括

    这项研究引入了一个新的框架,多细分度信心对齐平均教师 (MGCAMT),以改善无监督的跨域对象检测. 通过解决预测中的信心错位,MGCAMT改进了伪标签,以便在不同数据集中更准确地检测对象.

    科学领域:

    • 计算机科学 计算机科学
    • 人工智能的人工智能
    • 机器学习 机器学习

    背景情况:

    • 最先进的物体检测方法由于领域转移而难以概括.
    • 无监督的跨域对象检测旨在通过将知识从标记的源域转移到未标记的目标域来弥合这一差距.
    • 现有的平均教师方法看起来很有希望,但由于信任错位而受到次优伪标签的限制.

    研究的目的:

    • 为了应对未经监督的跨域对象检测伪标签中的信任错位的挑战.
    • 提出一个新的框架,多细分度信心对齐平均教师 (MGCAMT),同时在类别,实例和图像层面上对准信心.
    • 为了提高对象探测器在存在域移动时的准确性和概括性.

    主要方法:

    • 开发了多颗粒度信心对准平均教师 (MGCAMT) 框架.
    • 引入了使用证据深度学习 (EDL) 来建模类别不确定性和过不正确标签的分类信心对齐 (CCA).
    • 设计任务信心对齐 (TCA) 以减轻分类和本地化之间的实例级失调.
    • 实现图像聚焦信心对齐 (FCA) 实现了平衡的空间布局感知,没有明确的标签分配.

    主要成果:

    • 在类别,实例和图像层面上,MGCAMT有效地减轻了信心错位.

    更多相关视频

    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

    8.9K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    348

    相关实验视频

    Last Updated: May 24, 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

    451
    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

    8.9K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    348
  • 拟议的CCA,TCA和FCA组件有助于改进伪标签和改善教师与学生的学习.
  • 实验结果表明,与现有的最先进方法相比,在各种场景中,性能有了显著的改善.
  • 该框架显示了与大型基础模型相比的优越性能.

    • 结论:

    • 伪标签中的信任错位是无监督跨域对象检测中的关键瓶.
    • 通过整合多细分化的信任对齐策略,MGCAMT提供了一个强大的解决方案.
    • 拟议的方法显著提高了对象检测性能和概括能力,优于目前的方法.