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

Integrated scRNA-Seq and functional profiling reveal CD52 as a driver of pancreatic ductal adenocarcinoma metastasis and immunosuppression.

Oncogenesis·2026
Same author

Nab-paclitaxel plus S-1 induction chemotherapy for patients with locally advanced pancreatic cancer: a multicenter, open-label phase 2 study.

Signal transduction and targeted therapy·2026
Same author

AGR2-high cells drive a FOXM1-mediated pro-malignancy program in non-functional pancreatic neuroendocrine tumors (NF-PanNETs) and informatively predict patient outcomes.

Science bulletin·2026
Same author

Stearoyl-CoA Desaturase (SCD) Gene Based Molecular Breeding Enhances Nutritional Quality and Growth Performance in the Oyster (Crassostrea angulata).

Marine biotechnology (New York, N.Y.)·2026
Same author

Integration of Microbial Metabolic Regulation and Abiotic Oxidation: Mechanisms of Artificial Humic Acid-Enhanced Hydroxyl Radical Generation in Paddy Soil.

Research (Washington, D.C.)·2026
Same author

Remodeling the pancreatic tumor microenvironment by chemotherapy: New opportunities for combination therapy.

Biochimica et biophysica acta. Reviews on cancer·2026

相关实验视频

Updated: Jun 13, 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

层级智能互助信息元学习网络,用于短暂的细分.

Xiaoliu Luo, Zhao Duan, Anyong Qin

    IEEE transactions on neural networks and learning systems
    |September 10, 2024
    PubMed
    概括
    此摘要是机器生成的。

    本研究介绍了LayerMI,这是一种用于少数拍摄细分 (FSS) 的新型元学习框架. 层MI通过最大化相互信息来增强图像之间的标签信息传输,提高未见类的细分精度.

    更多相关视频

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    378
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    8.6K

    相关实验视频

    Last Updated: Jun 13, 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
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    378
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    8.6K

    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:

    • 少数镜头细分 (FSS) 旨在对具有有限标记数据的新型类别的图像进行细分.
    • 标签信息从支持到查询图像的有效转移对于FSS的性能至关重要.

    研究的目的:

    • 引入一个新的元学习框架,LayerMI,以加强标签信息在FSS中的传播.
    • 提高细分对象类的准确性和效率,以前从未见过.

    主要方法:

    • 开发了一个使用基于信息理论协集群的LayerMI块的LayerMI框架.
    • 在每个卷积神经网络 (CNN) 层中,支持和查询图像特征之间的最大化相互信息 (MI).
    • 集成层MI块融入现有元学习框架,而不会改变培训目标.

    主要成果:

    • 层MI显著提高了基线FSS模型的性能.
    • 在PASCAL-$5^i$,COCO-$20^i$和FSS-1000基准上,与最先进的方法相比,取得了具有竞争力的结果.
    • 证明了LayerMI能够促进内部图像集群的功能,同时最大限度地实现图像间MI.

    结论:

    • 拟议的LayerMI框架有效地增强了标签信息的传播,以实现短暂的细分.
    • 层MI提供了一种灵活而强大的方法来改进新类的细分.
    • 这种方法显示出强大的潜力,可以推进少量学习领域的发展.