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

Cryoballoon ablation for Barrett neoplasia: durability and attribution require caution.

Endoscopy·2026
Same author

Risk stratification for reoperation outcomes in recurrent or persistent papillary thyroid carcinoma: development and validation of a machine learning model.

BMC medical informatics and decision making·2026
Same author

Methodologic and analytic considerations regarding the estrogen-responsive ORMDL3-S1P axis in asthma.

The Journal of allergy and clinical immunology·2026
Same author

Letter to the Editor: "INTERACT3 in Intensive Blood Pressure Meta-analysis: A Methodological Reappraisal".

Neurocritical care·2026
Same author

Zinc oxide quantum dots as an alternative to conventional ZnO: Physicochemical characterization and its application in weaned piglets.

Animal nutrition (Zhongguo xu mu shou yi xue hui)·2026
Same author

Reassessing Cancer Attribution and Methodological Limitations in PLA2R-Associated Membranous Nephropathy.

Mayo Clinic proceedings·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
查看所有相关文章

相关实验视频

Updated: Jun 25, 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

无监督域的自适应细分算法,基于两级类别对齐.

Wenyong Dong1, Zhixue Liang2, Liping Wang3

  • 1School of Computer Science, Wuhan University, Wuhan, 430072, China; School of Information Network Security, Xinjiang University of Political Science and Law, Tumushuke, 843900, China.

Neural networks : the official journal of the International Neural Network Society
|May 28, 2024
PubMed
概括
此摘要是机器生成的。

本研究引入了一种新的无监督域自适应算法 (UDAca+),通过在图像和像素层面对准类别信息来改进语义细分. 这种方法增强了特征表示,以便在域调整任务中获得更好的细分精度.

关键词:
班级激活地图 班级激活地图生成性的对抗性网络.语义细分 语义细分是指语义细分.两个级别的类别调整对齐.无监督的域名适应.

更多相关视频

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K

相关实验视频

Last Updated: Jun 25, 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
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K

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:

  • 用于语义细分的无监督域调整 (UDA) 常常忽略了类别信息,仅专注于像素级本地特征.
  • 这种限制阻碍了对特定类别的域间不变特征的学习,从而对细分性能产生负面影响.

研究的目的:

  • 开发一个有效的UDA算法,利用类别信息来改进语义细分.
  • 通过结合图像级和像素级分类对齐来解决现有方法的局限性.

主要方法:

  • 拟议的UDAca+算法具有两级分类对齐:图像级使用类激活地图 (CAM) 和像素级使用伪标签.
  • 在网络培训的混合领域实施了对抗式学习策略.
  • 引入了一种信任计算方法,以减轻噪音图像级伪标签的问题,例如负转移和过度调整.

主要成果:

  • UDAca+有效地捕获域不变,类别歧视性特征表示,从而提高了细分精度.
  • 在两个合成到现实适应任务中实现了最先进的 (SOTA) 性能.
  • 证明了算法的有效性,改善了域调整场景中的图像细分.

结论:

  • 拟议的UDAca+算法通过有效利用类别信息,显著推进无监督域自适应语义细分.
  • 两级类别对齐策略和信任计算方法为域调整挑战提供了强大的解决方案.