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

HER2 assessment in locally advanced gastric cancer: comparing the results obtained with the use of two primary tumour blocks versus those obtained with the use of all primary tumour blocks.

Histopathology·2017
Same author

Inflammatory microRNA-194 and -515 attenuate the biosynthesis of chondroitin sulfate during human intervertebral disc degeneration.

Oncotarget·2017
Same author

Soil Acidification Aggravates the Occurrence of Bacterial Wilt in South China.

Frontiers in microbiology·2017
Same author

Is the Prophylactic Use of Hepatoprotectants Necessary in Anti-Tuberculosis Treatment?

Chemotherapy·2017
Same author

Light-induced aggregation of microbial exopolymeric substances.

Chemosphere·2017
Same author

Chemical Synthesis of (+)-Ryanodine and (+)-20-Deoxyspiganthine.

ACS central science·2017
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
查看所有相关文章

相关实验视频

Updated: Jul 26, 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

2.8K

学习形状不变表示用于可概括的语义细分.

Yuhang Zhang, Shishun Tian, Muxin Liao

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
    |June 22, 2023
    PubMed
    概括
    此摘要是机器生成的。

    本研究介绍了形状不变学习 (SIL) 用于语义细分领域的概括. SIL学习形状不变表示,以提高在没有目标数据的未见域上的模型性能.

    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

    9.0K
    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

    585

    相关实验视频

    Last Updated: Jul 26, 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

    2.8K
    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
    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

    585

    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:

    • 监督的语义细分优越,但由于域间隙,与域泛化作斗争.
    • 现有的域调整方法需要目标数据,限制它们在不可用域中的使用.
    • 域泛化 (DG) 旨在训练在没有目标数据的未见域上表现良好的模型.

    研究的目的:

    • 开发一个新的框架,用于语义细分领域的泛化,解决领域的差距.
    • 通过学习形状不变表示来改善模型概括,专注于跨域对象形状差异.
    • 在新的,不可用域中增强语义细分性能.

    主要方法:

    • 提出了一个形状不变学习 (SIL) 框架,以学习形状不变表示,以便更好地概括.
    • 定义了"结构边缘",结合了对象边界和内部结构,以加强区分.
    • 实施了一种形状感知学习策略,其中包括纹理和结构特征差异损失,以及形状变形增强.

    主要成果:

    • SIL框架有效地学习形状不变表示,通过在域级别内隐含地对准形状分布.
    • 实验结果表明,在域泛化任务中,拟议的SIL框架具有最先进的性能.
    • 这种方法通过将结构边缘嵌入为形状先验,成功地提高了形状感知能力.

    结论:

    • 形状不变学习 (SIL) 框架显著改善了语义细分领域的泛化.
    • 学习形状不变表示对于跨越多样化和未见的领域的强大性能至关重要.
    • 提出的方法为解决语义细分领域转移挑战提供了一个有希望的方向.