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

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

900
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
900

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

Semi-supervised atmospheric component learning in low-light image problem.

PloS one·2023
Same author

Can hippocampal subfield measures supply information that could be used to improve the diagnosis of Alzheimer's disease?

PloS one·2022
Same author

Denoising Single Images by Feature Ensemble Revisited.

Sensors (Basel, Switzerland)·2022
Same author

Rethinking Gradient Weight's Influence over Saliency Map Estimation.

Sensors (Basel, Switzerland)·2022
Same author

Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging.

PloS one·2020
Same author

Fast Single-Image HDR Tone-Mapping by Avoiding Base Layer Extraction.

Sensors (Basel, Switzerland)·2020

相关实验视频

Updated: Jul 5, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

774

提高合奏学习使用可解释的CNN伪造指纹.

Naim Reza1, Ho Yub Jung1

  • 1Department of Computer Engineering, Chosun University, Gwangju 61452, Republic of Korea.

Sensors (Basel, Switzerland)
|January 11, 2024
PubMed
概括
此摘要是机器生成的。

本研究引入了一种新的卷积神经网络 (CNN) 训练方法,使用类激活地图 (CAM) 来提高分类的准确性和稳定性. 通过专注于不同的数据区域,组合网络可以实现最先进的结果.

关键词:
班级激活地图的地图.卷积神经网络是一种卷积神经网络.组合学习组合学习指纹指纹指纹指纹指纹指纹伪造检测 伪造检测 伪造检测

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

556
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

494

相关实验视频

Last Updated: Jul 5, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

774
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

556
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

494

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 卷积神经网络 (CNN) 在分类方面表现出色,但缺乏可解释性,这引发了对有限数据可靠性的担忧.
  • 使用多个CNN进行集体学习可以提高稳定性,但往往以精度为代价.
  • 训练数据有限对CNN的可靠性和稳定性构成挑战.

研究的目的:

  • 提出一种新的CNN训练方法,提高准确性和稳健性.
  • 解决基于CNN的分类系统中的可解释性和可靠性问题.
  • 通过新的合奏方法,改善CNN在有限的训练数据集上的表现.

主要方法:

  • 利用班级激活地图 (CAM) 识别先前训练有素的CNN中具有影响力的地区.
  • 在培训新的CNN时,隐藏了已识别的"指纹"区域,具有相同架构的CNN.
  • 集成的结果网络,以确保对分类进行全面的特征考虑.

主要成果:

  • 在多个传感器上实现了对分类准确度和稳定性的显著提升.
  • 在LivDet数据集上展示了最先进的准确性.
  • 这种新的训练方法提高了CNN预测的可靠性和一致性.

结论:

  • 提出的基于CAM的培训方法有效地提高了CNN的准确性和稳定性.
  • 这种方法减轻了经常在合并方法中看到的准确性-稳定性权衡.
  • 该技术为基于CNN的分类提供了可靠的解决方案,特别是在数据有限的情况下.