An efficient feature reuse distillation network for lightweight image super-resolution

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Computer Vision and Image Understanding Pub Date : 2024-09-27 DOI:10.1016/j.cviu.2024.104178
Chunying Liu , Guangwei Gao , Fei Wu , Zhenhua Guo , Yi Yu
{"title":"An efficient feature reuse distillation network for lightweight image super-resolution","authors":"Chunying Liu ,&nbsp;Guangwei Gao ,&nbsp;Fei Wu ,&nbsp;Zhenhua Guo ,&nbsp;Yi Yu","doi":"10.1016/j.cviu.2024.104178","DOIUrl":null,"url":null,"abstract":"<div><div>In recent research, single-image super-resolution (SISR) using deep Convolutional Neural Networks (CNN) has seen significant advancements. While previous methods excelled at learning complex mappings between low-resolution (LR) and high-resolution (HR) images, they often required substantial computational and memory resources. We propose the Efficient Feature Reuse Distillation Network (EFRDN) to alleviate these challenges. EFRDN primarily comprises Asymmetric Convolutional Distillation Modules (ACDM), incorporating the Multiple Self-Calibrating Convolution (MSCC) units for spatial and channel feature extraction. It includes an Asymmetric Convolution Residual Block (ACRB) to enhance the skeleton information of the square convolution kernel and a Feature Fusion Lattice Block (FFLB) to convert low-order input signals into higher-order representations. Introducing a Transformer module for global features, we enhance feature reuse and gradient flow, improving model performance and efficiency. Extensive experimental results demonstrate that EFRDN outperforms existing methods in performance while conserving computing and memory resources.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002595","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

In recent research, single-image super-resolution (SISR) using deep Convolutional Neural Networks (CNN) has seen significant advancements. While previous methods excelled at learning complex mappings between low-resolution (LR) and high-resolution (HR) images, they often required substantial computational and memory resources. We propose the Efficient Feature Reuse Distillation Network (EFRDN) to alleviate these challenges. EFRDN primarily comprises Asymmetric Convolutional Distillation Modules (ACDM), incorporating the Multiple Self-Calibrating Convolution (MSCC) units for spatial and channel feature extraction. It includes an Asymmetric Convolution Residual Block (ACRB) to enhance the skeleton information of the square convolution kernel and a Feature Fusion Lattice Block (FFLB) to convert low-order input signals into higher-order representations. Introducing a Transformer module for global features, we enhance feature reuse and gradient flow, improving model performance and efficiency. Extensive experimental results demonstrate that EFRDN outperforms existing methods in performance while conserving computing and memory resources.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于轻量级图像超分辨率的高效特征重用蒸馏网络
近年来,使用深度卷积神经网络(CNN)的单图像超分辨率(SISR)研究取得了重大进展。虽然以前的方法擅长学习低分辨率(LR)和高分辨率(HR)图像之间的复杂映射,但它们往往需要大量的计算和内存资源。我们提出了高效特征重用蒸馏网络(EFRDN)来缓解这些挑战。EFRDN 主要由非对称卷积蒸馏模块(ACDM)组成,其中包含用于空间和信道特征提取的多重自校准卷积(MSCC)单元。它包括一个非对称卷积残差块(ACRB),用于增强方形卷积核的骨架信息,以及一个特征融合网格块(FFLB),用于将低阶输入信号转换为高阶表示。通过引入全局特征变换器模块,我们增强了特征重用和梯度流,从而提高了模型的性能和效率。广泛的实验结果表明,EFRDN 的性能优于现有方法,同时节约了计算和内存资源。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
期刊最新文献
Diffusion Models for Counterfactual Explanations Image compressive sensing reconstruction via nonlocal low-rank residual-based ADMM framework A MLP architecture fusing RGB and CASSI for computational spectral imaging A GCN and Transformer complementary network for skeleton-based action recognition Invisible backdoor attack with attention and steganography
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1