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

Collapse of hybrid vector beam in Rb atomic vapor.

Optics letters·2021
Same author

Self-Treatment of Posterior Canal Benign Paroxysmal Positional Vertigo: A Preliminary Study.

Frontiers in medicine·2021
Same author

GCN2 Regulates ATF3-p38 MAPK Signaling Transduction in Pulmonary Veno-Occlusive Disease.

Journal of cardiovascular pharmacology and therapeutics·2021
Same author

Serum Levels of ITGBL1 as an Early Diagnostic Biomarker for Hepatocellular Carcinoma with Hepatitis B Virus Infection.

Journal of hepatocellular carcinoma·2021
Same author

Mixotrophic Chlorella pyrenoidosa as cell factory for ultrahigh-efficient removal of ammonium from catalyzer wastewater with valuable algal biomass coproduction through short-time acclimation.

Bioresource technology·2021
Same author

The Gene Signature Associated with Hepatocellular Carcinoma in Patients with Nonalcoholic Fatty Liver Disease.

Journal of oncology·2021

相关实验视频

Updated: Jul 23, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

442

MADAv2:先进的多基主动域适应细分化.

Munan Ning, Donghuan Lu, Yujia Xie

    IEEE transactions on pattern analysis and machine intelligence
    |July 11, 2023
    PubMed
    概括

    本研究介绍了在语义细分中进行无监督域适应的活跃样本选择. 通过选择具有信息性的目标域样本,它显著提高了性能,接近完全监督的结果.

    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:

    • 无监督的域调整对于具有有限注释数据的任务至关重要.
    • 标准方法可能会扭曲目标域数据结构,降低性能.
    • 语义细分经常面临由于域移动的挑战.

    研究的目的:

    • 改进无监督域适应用于语义细分.
    • 为了减轻无条件分布映射引起的性能下降.
    • 引入一个更有效的样本选择策略.

    主要方法:

    • 建议使用多个点进行主动抽样选择,以表征多式联络分布.
    • 开发了一个半监督的域名适应策略,以解决长尾分布.
    • 利用创新技术更好地表示源域和目标域.

    主要成果:

    • 通过减轻目标域分布扭曲,实现了显著的性能增长.
    • 在公共数据集 (GTA5,SYNTHIA) 上超越了最先进的方法.
    • 达到与完全监督方法相比的性能 (GTA5上的71.4% mIoU,SYNTHIA上的71.8% mIoU).

    结论:

    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
    Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
    12:50

    Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

    Published on: April 14, 2014

    40.3K

    相关实验视频

    Last Updated: Jul 23, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    442
    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
    Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
    12:50

    Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

    Published on: April 14, 2014

    40.3K
    • 积极的样本选择有效地提高了无监督域的适应性.
    • 拟议的半监督策略进一步提高了细分业绩.
    • 该方法在语义细分任务中表现出卓越的有效性和稳定性.