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

Hand-Object Pose Estimation Based on Anchor Regression from a Single Egocentric Depth Image.

Sensors (Basel, Switzerland)·2025
Same author

One stage multi-scale efficient network for underwater target detection.

The Review of scientific instruments·2024
Same author

MBA-DNet: A mask block attention-based foreign matter detection network for tobacco packages.

The Review of scientific instruments·2024
Same author

Effects of GLP-1 receptor agonists on asprosin levels in normal weight or overweight/obesity patients with type 2 diabetes mellitus.

Medicine·2022
Same author

Multiple heavy metals immobilization based on microbially induced carbonate precipitation by ureolytic bacteria and the precipitation patterns exploration.

Chemosphere·2021
Same author

[Collateral supply in patients with severe carotid stenosis].

Zhonghua yi xue za zhi·2007
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
查看所有相关文章

相关实验视频

Updated: Mar 15, 2026

Fluorescence detection methods for microfluidic droplet platforms
14:16

Fluorescence detection methods for microfluidic droplet platforms

Published on: December 10, 2011

23.0K

SD-IDD:用于增量缺陷检测的选择性蒸.

Jing Li1, Chenggang Dai1, Xiaobin Wang1

  • 1School of Mechanical and Automotive Engineering, Qingdao University of Technology, Qingdao 266000, China.

Sensors (Basel, Switzerland)
|March 14, 2026
PubMed
概括
此摘要是机器生成的。

本研究引入了增量缺陷检测 (SD-IDD) 模型的选择性蒸,以防止深度学习中的灾难性遗忘. 这种新的方法提高了新表面缺陷类别的检测精度,而没有旧数据.

关键词:
灾难性的遗忘.增量学习是一种增量学习.选择性蒸是一种选择性蒸.

更多相关视频

3D Depth Profile Reconstruction of Segregated Impurities Using Secondary Ion Mass Spectrometry
07:10

3D Depth Profile Reconstruction of Segregated Impurities Using Secondary Ion Mass Spectrometry

Published on: April 29, 2020

2.1K
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.6K

相关实验视频

Last Updated: Mar 15, 2026

Fluorescence detection methods for microfluidic droplet platforms
14:16

Fluorescence detection methods for microfluidic droplet platforms

Published on: December 10, 2011

23.0K
3D Depth Profile Reconstruction of Segregated Impurities Using Secondary Ion Mass Spectrometry
07:10

3D Depth Profile Reconstruction of Segregated Impurities Using Secondary Ion Mass Spectrometry

Published on: April 29, 2020

2.1K
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.6K

科学领域:

  • 工业工程 工业工程 工业工程
  • 计算机科学 计算机科学
  • 人工智能的人工智能

背景情况:

  • 工业环境中的表面缺陷是多样化和不断变化的.
  • 深度学习模型在学习新缺陷类型时与灾难性遗忘作斗争.
  • 现有的方法往往需要旧的培训数据进行再培训.

研究的目的:

  • 开发一个增量缺陷检测模型,减轻灾难性遗忘.
  • 提高深度学习模型对新缺陷类别的适应性.
  • 提高旧和新缺陷类别的检测准确度,而无需对旧数据进行重新训练.

主要方法:

  • 提出了基于GFLv1.1的增量缺陷检测 (SD-IDD) 模型的选择性蒸.
  • 实施了三种选择性蒸策略:高可靠性分类,双阶段级级回归和IOU驱动的难度感知特征蒸.
  • 利用IOU加权的KL差异来实现准确的本地化知识转移和适应性资源分配,以应对困难的目标.

主要成果:

  • SD-IDD显著缓解了灾难性遗忘.
  • 在NEU-DET和DeepPCB数据集上实现了卓越的性能.
  • 证明了高的mAP_old (58.2%,99.3%) 和mAP_new (69.0%,97.3%) 分数,表现优于现有的增量检测方法.

结论:

  • 拟议的SD-IDD模型有效地解决了在增量缺陷检测中的灾难性遗忘问题.
  • 选择性蒸策略提高了新缺陷类别的检测准确度.
  • 该方法实现了最先进的性能,而不需要访问以前的训练样本.