Search research articles

Search research articles

相关实验视频

Updated: Jun 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

EHNet:高效的混合网络,双重关注图像消除模糊.

Quoc-Thien Ho¹, Minh-Thien Duong², Seongsoo Lee³

¹Department of Information and Telecommunication Engineering, Soongsil University, Seoul 06978, Republic of Korea.

Sensors (Basel, Switzerland)

|October 26, 2024

概括

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

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

Sensors (Basel, Switzerland)·2026

Same author

Adaptive Image Deblurring Convolutional Neural Network with Meta-Tuning.

Sensors (Basel, Switzerland)·2025

Same author

Adaptive Autoencoder-Based Intrusion Detection System with Single Threshold for CAN Networks.

Sensors (Basel, Switzerland)·2025

Same author

Multi-Branch Network for Color Image Denoising Using Dilated Convolution and Attention Mechanisms.

Sensors (Basel, Switzerland)·2024

Same author

A Novel Architecture for an Intrusion Detection System Utilizing Cross-Check Filters for In-Vehicle Networks.

Sensors (Basel, Switzerland)·2024

Same author

CNN-Based Facial Expression Recognition with Simultaneous Consideration of Inter-Class and Intra-Class Variations.

Sensors (Basel, Switzerland)·2023

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

本研究介绍了一种高效混合网络 (EHNet),用于图像消除模糊,它结合了CNN和变压器. 这种新型网络有效地消除了模糊文物,提高了图像质量,降低了计算成本.

科学领域:

计算机视觉计算机视觉
人工智能的人工智能
图像处理图像处理

背景情况:

动作导致的图像模糊是成像中的一个重大挑战,降低了图像质量.
深度学习,特别是卷积神经网络 (CNN) 和变压器,显示出对图像消除模糊性的承诺.
现有的方法面临局限性:CNN限制了受感场,而变压器是计算密集的,缺乏诱导偏差.

研究的目的:

开发一种高效的基于深度学习的图像处理方法,以有效地去除模糊文物.
为了克服现有的CNN和变压器架构在图像模糊化方面的局限性.
提出一种新的混合网络,可以平衡本地特征提取和远程依赖模型.

主要方法:

提出了一个高效的混合网络 (EHNet),利用CNN编码器用于本地特征和变压器解码器用于全球环境.
在变压器解码器中引入了双重注意模块,以捕获空间和通道智能的依赖性.
开发了一个简单的功能嵌入模块 (SFEM),以减少自我注意机制中的计算复杂性.

主要成果:

EHNet模型展示了高质量的图像消除模糊性的功能.
对基准数据集的全面实验显示出有希望的定量和定性结果.
在不影响性能的情况下,SFEM显著降低了计算复杂性和内存使用量.

关键词:

变压器变压器变压器卷积神经网络是一个卷积神经网络.双重注意力模块是双重注意力的模块.混合架构架构是混合架构的架构.图像消除模糊的方法运动模糊模糊模糊

更多相关视频

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

相关实验视频

Last Updated: Jun 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

结论:

拟议的EHNet提供了一种高效和有效的解决方案来消除图像模糊.
混合方法成功地整合了CNN和变形金刚的优势.
这项工作推进了基于深度学习的图像消除模糊,使用计算效率高和高性能模型.