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

Sub-second volumetric 3D printing by synthesis of holographic light fields.

Nature·2026
Same author

Detecting sarcasm in user-generated content integrating transformers and gated graph neural networks.

PeerJ. Computer science·2025
Same author

Multimodal GRU with directed pairwise cross-modal attention for sentiment analysis.

Scientific reports·2025
Same author

Empowering legal justice with AI: A reinforcement learning SAC-VAE framework for advanced legal text summarization.

PloS one·2024
Same author

Beyond surveillance: privacy, ethics, and regulations in face recognition technology.

Frontiers in big data·2024
Same author

Draft genome of <i>Pseudomonas</i> sp. XK-1, a marine bacterium capable of degrading lignin and Mn(II) oxidation.

Microbiology resource announcements·2024

相关实验视频

Updated: Jul 6, 2025

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

未标记的数据选择,用于图像分类中的积极学习.

Xiongquan Li1, Xukang Wang2, Xuhesheng Chen3

  • 1Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China.

Scientific reports
|January 3, 2024
PubMed
概括
此摘要是机器生成的。

积极学习 (AL) 方法有效地选择信息图像用于训练计算机视觉模型. 新的AL技术显著改善了用于图像分类的数据选择,减少了注释需求.

更多相关视频

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
07:31

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

6.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

相关实验视频

Last Updated: Jul 6, 2025

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
Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
07:31

Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

Published on: February 8, 2019

6.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 数据科学数据科学数据科学

背景情况:

  • 积极学习 (AL) 解决了在数据密集型领域广泛数据标签的挑战.
  • AL旨在识别有价值的未标记的数据样本,以便使用获取函数进行注释.
  • 计算机视觉中的图像分类需要大量的训练数据集.

研究的目的:

  • 引入创新的AL选择方法用于图像分类.
  • 从未标记的数据集中识别信息图像.
  • 尽量减少有效的模型训练所需的训练数据量.

主要方法:

  • 开发了基于相似性的选择,基于预测概率的选择和基于能力的积极学习方法.
  • 评估了Cifar10和Cifar100数据集上的拟议方法.
  • 将新方法与随机和传统的选择技术进行比较.

主要成果:

  • 拟议的AL方法与随机选择相比显示出更高的性能.
  • 新技术的表现优于传统的数据选择方法.
  • 证明了提高图像分类的AL过程的有效性.

结论:

  • 新的选择方法在图像分类中的积极学习中是有效的.
  • 这些方法减少了对大量数据注释的需求.
  • 在计算机视觉任务的AL过程中取得了显著的改进.