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

VITAL: Value-Invariant Transformation and Alignment Learning for quantitative photoacoustic microscopy.

Photoacoustics·2026
Same author

Integrated genomic and phenotypic analysis of an endophytic bacterium reveals biocontrol and plant growth-promoting mechanisms.

iScience·2026
Same author

New insights into polycyclic aromatic hydrocarbons: Phenanthrene targets ribosomes to induce neuronal apoptosis.

Aquatic toxicology (Amsterdam, Netherlands)·2026
Same author

A frame-difference-aware rockburst early warning method based on the spatiotemporal distribution of microseismicity in deep mines.

Environmental research·2026
Same author

Macrophage autophagy-dependent M2 polarization mediates the protective effect of ADSC-conditioned medium against acute lung injury.

Stem cell research & therapy·2026
Same author

Integrating network toxicology, transcriptomics and experimental validation to elucidate the potential mechanisms of fluoride-induced neurotoxicity in zebrafish.

Comparative biochemistry and physiology. Toxicology & pharmacology : CBP·2026
Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026
Same journal

Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

IEEE transactions on neural networks and learning systems·2026
Same journal

cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

IEEE transactions on neural networks and learning systems·2026
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
查看所有相关文章

相关实验视频

Updated: Jul 12, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

437

对于半监督的缺陷细分的扰乱渐进式学习.

Yao Wu, Mingwei Xing, Yachao Zhang

    IEEE transactions on neural networks and learning systems
    |October 24, 2023
    PubMed
    概括
    此摘要是机器生成的。

    扰乱渐进式学习 (PPL) 通过使用有限的标记数据来解决缺陷细分方面的挑战. 这种半监督的缺陷细分方法提高了智能制造表面检查的准确性.

    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
    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
    11:38

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

    Published on: August 23, 2017

    9.9K

    相关实验视频

    Last Updated: Jul 12, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    437
    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
    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
    11:38

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

    Published on: August 23, 2017

    9.9K

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 智能制造是一个智能制造.

    背景情况:

    • 表面缺陷检查对于智能制造至关重要,随着需求的增加.
    • 深度学习显示出有希望的结果,但与罕见的缺陷数据和困难的pixelwise注释作斗争.
    • 由于数据限制,现有的监督方法通常是不切实际的.

    研究的目的:

    • 为具有有限标记数据的场景提出半监督缺陷细分 (SSDS) 方法.
    • 开发一种高效简单的方法,称为扰乱渐进式学习 (PPL).
    • 为了提高工业应用中的缺陷细分精度.

    主要方法:

    • PPL使用学生-教师网络架构来解预测,并减少噪音杂的伪标签的过度匹配.
    • 它鼓励以阶段式的方式在干扰中保持一致,以减轻标签漂移.
    • 该方法涉及两个阶段:初始伪标签易/难无标签数据和使用扰乱数据的逐步细化.

    主要成果:

    • 在新的移动屏幕缺陷数据集 (MSDD-3) 和公共数据集上评估了PPL.
    • 该方法在各种评估协议中显示出与最先进的技术相比的显著改进.
    • 实验结果证实了PPL在缺陷细分中的有效性,标签有限.

    结论:

    • 扰乱渐进式学习 (PPL) 为半监督缺陷细分提供了一个有效的解决方案.
    • 该方法克服了罕见缺陷数据和智能制造中的复杂注释的局限性.
    • PPL显著提高了缺陷检查能力,超过了现有的方法.