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

Gender differences in mental health profiles among Chinese adolescents: a multiple-group latent profile analysis.

BMC psychology·2026
Same author

Machine learning-based predictive factor analysis of depression among Chinese adolescents.

Frontiers in psychiatry·2026
Same author

Miltefosine attenuates silicosis involving inhibiting the Akt/mTOR signaling pathway.

European journal of pharmacology·2026
Same author

Uncovering the determinants of infant and toddler childcare demand in less-developed rural China: a machine learning perspective.

Frontiers in public health·2026
Same author

Kynurenine-AhR-SLC39A10-Zn<sup>2+</sup> signaling reprograms macrophages and enhances pirfenidone efficacy in pulmonary fibrosis.

Cell communication and signaling : CCS·2026
Same author

Shifting resource dominance in career decision-making difficulties: a competitive mediation model of resilience and general self-efficacy among Chinese university students.

Frontiers in psychology·2026

相关实验视频

Updated: Jun 5, 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

以照明为导向的渐进无监督域调整,用于低光实例细分.

Yi Zhang1, Jichang Guo2, Huihui Yue3

  • 1School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China.

Neural networks : the official journal of the International Neural Network Society
|December 5, 2024
PubMed
概括

这项研究介绍了IPULIS,一种以照明为导向的方法,用于在低光条件下改善计算机视觉. 它通过逐步在不同层次上对齐功能来改善实例细分,从而实现最先进的结果.

关键词:
实例细分是指实例的细分.在低光照明下拍摄的图像.视网膜x 视网膜x 是一个无监督的域名适应

更多相关视频

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

468
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

相关实验视频

Last Updated: Jun 5, 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
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

468
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 图像处理 图像处理

背景情况:

  • 由于光子有限,低光条件极大地挑战了计算机视觉任务.
  • 无监督的域适应方法在低光场景中与域错位作斗争.
  • 不足够的功能在不同阶段的利用阻碍了性能.

研究的目的:

  • 为低光实例细分提出一个照明引导的渐进无监督域适应方法 (IPULIS).
  • 在正常和低光域之间逐渐调整图像,实例和像素级别的特征.
  • 为了提高功能利用率和解决域错位问题.

主要方法:

  • 开发了一种照明引导域区分器 (IGD),用于使用视网膜衍生照明图进行图像级对齐.
  • 引入了前景焦点模块 (FFM),通过整合全球和本地特征来实现实例级对齐.
  • 实现了边形感知域区分器 (CAD) 用于使用边形顶点特征进行像素级对齐.

主要成果:

  • 通过逐步部署模块,IPULIS可以实现精确的特征对齐.
  • 该方法可以在低光环境中实现高质量的实例细分.
  • 在LIS真实世界低光数据集上展示了最先进的性能.

结论:

  • IPULIS有效地解决了低光电脑视觉方面的挑战.
  • 渐进的,照明引导的特征对齐可以提高实例细分的准确性.
  • 拟议的方法为现实世界低光应用提供了强大的解决方案.