OMLK-Net:一种用于图像超分辨率的在线多尺度大可分离核蒸馏网络

IF 3.4 2区 工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Hanjia Wei, Weiwei Wang, Xixi Jia, Xiangchu Feng, Chuan Chen
{"title":"OMLK-Net:一种用于图像超分辨率的在线多尺度大可分离核蒸馏网络","authors":"Hanjia Wei,&nbsp;Weiwei Wang,&nbsp;Xixi Jia,&nbsp;Xiangchu Feng,&nbsp;Chuan Chen","doi":"10.1016/j.sigpro.2025.110078","DOIUrl":null,"url":null,"abstract":"<div><div>Single-image super-resolution (SISR) has seen remarkable progress in recent years, driven by the powerful learning capabilities of large-scale neural networks, such as deep CNNs and Transformers. However, these advances come at the expense of substantial computational costs. Striking a delicate balance between effectiveness and efficiency remains a key challenge in neural network design. This paper proposes OMLK-Net, a novel lightweight architecture for SISR, offering the dual advantages of computational efficiency and high effectiveness. OMLK-Net adopts a divide-and-conquer strategy to separately optimize local and nonlocal feature learning, enabling a lightweight architecture without compromising feature representation effectiveness. Specifically, our OMLK-Net comprises two key modules: an Online Multiscale Distillation Block (OMDB) and Large Separable Shifting Kernel Attention (L2SKA) blocks. The OMDB module aims to explore multiscale local contextual information with a customized lightweight network block; while the L2SKA aims to harness nonlocal features by using computationally efficient large separable shifting kernels. By virtue of its carefully designed local and nonlocal feature extraction operators, OMLK-Net effectively addresses SISR challenges while maintaining low computational complexity. Extensive experimental results on benchmark datasets demonstrate that OMLK-Net achieves a better trade-off against state-of-the-art methods in terms of performance and model complexity. Codes will be available soon.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"237 ","pages":"Article 110078"},"PeriodicalIF":3.4000,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"OMLK-Net: An Online Multi-scale Large Separable Kernel Distillation Network for efficient image super-resolution\",\"authors\":\"Hanjia Wei,&nbsp;Weiwei Wang,&nbsp;Xixi Jia,&nbsp;Xiangchu Feng,&nbsp;Chuan Chen\",\"doi\":\"10.1016/j.sigpro.2025.110078\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Single-image super-resolution (SISR) has seen remarkable progress in recent years, driven by the powerful learning capabilities of large-scale neural networks, such as deep CNNs and Transformers. However, these advances come at the expense of substantial computational costs. Striking a delicate balance between effectiveness and efficiency remains a key challenge in neural network design. This paper proposes OMLK-Net, a novel lightweight architecture for SISR, offering the dual advantages of computational efficiency and high effectiveness. OMLK-Net adopts a divide-and-conquer strategy to separately optimize local and nonlocal feature learning, enabling a lightweight architecture without compromising feature representation effectiveness. Specifically, our OMLK-Net comprises two key modules: an Online Multiscale Distillation Block (OMDB) and Large Separable Shifting Kernel Attention (L2SKA) blocks. The OMDB module aims to explore multiscale local contextual information with a customized lightweight network block; while the L2SKA aims to harness nonlocal features by using computationally efficient large separable shifting kernels. By virtue of its carefully designed local and nonlocal feature extraction operators, OMLK-Net effectively addresses SISR challenges while maintaining low computational complexity. Extensive experimental results on benchmark datasets demonstrate that OMLK-Net achieves a better trade-off against state-of-the-art methods in terms of performance and model complexity. Codes will be available soon.</div></div>\",\"PeriodicalId\":49523,\"journal\":{\"name\":\"Signal Processing\",\"volume\":\"237 \",\"pages\":\"Article 110078\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Signal Processing\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0165168425001926\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Signal Processing","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0165168425001926","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

近年来,在大规模神经网络(如深度cnn和Transformers)强大的学习能力的推动下,单图像超分辨率(SISR)取得了显著进展。然而,这些进步是以大量的计算成本为代价的。在有效性和效率之间取得微妙的平衡仍然是神经网络设计的关键挑战。本文提出了一种新型的轻量级SISR体系结构OMLK-Net,它具有计算效率高和效率高的双重优点。OMLK-Net采用分而治之的策略分别优化局部和非局部特征学习,在不影响特征表示效率的情况下实现轻量级体系结构。具体来说,我们的OMLK-Net包括两个关键模块:在线多尺度蒸馏块(OMDB)和大可分离转移核注意块(L2SKA)。OMDB模块旨在通过定制的轻量级网络块探索多尺度本地上下文信息;而L2SKA则旨在通过使用计算效率高的大可分离移位核来利用非局部特征。由于其精心设计的局部和非局部特征提取算子,OMLK-Net有效地解决了SISR挑战,同时保持了较低的计算复杂度。在基准数据集上的大量实验结果表明,OMLK-Net在性能和模型复杂性方面比最先进的方法取得了更好的折衷。代码将很快提供。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
OMLK-Net: An Online Multi-scale Large Separable Kernel Distillation Network for efficient image super-resolution
Single-image super-resolution (SISR) has seen remarkable progress in recent years, driven by the powerful learning capabilities of large-scale neural networks, such as deep CNNs and Transformers. However, these advances come at the expense of substantial computational costs. Striking a delicate balance between effectiveness and efficiency remains a key challenge in neural network design. This paper proposes OMLK-Net, a novel lightweight architecture for SISR, offering the dual advantages of computational efficiency and high effectiveness. OMLK-Net adopts a divide-and-conquer strategy to separately optimize local and nonlocal feature learning, enabling a lightweight architecture without compromising feature representation effectiveness. Specifically, our OMLK-Net comprises two key modules: an Online Multiscale Distillation Block (OMDB) and Large Separable Shifting Kernel Attention (L2SKA) blocks. The OMDB module aims to explore multiscale local contextual information with a customized lightweight network block; while the L2SKA aims to harness nonlocal features by using computationally efficient large separable shifting kernels. By virtue of its carefully designed local and nonlocal feature extraction operators, OMLK-Net effectively addresses SISR challenges while maintaining low computational complexity. Extensive experimental results on benchmark datasets demonstrate that OMLK-Net achieves a better trade-off against state-of-the-art methods in terms of performance and model complexity. Codes will be available soon.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Signal Processing
Signal Processing 工程技术-工程:电子与电气
CiteScore
9.20
自引率
9.10%
发文量
309
审稿时长
41 days
期刊介绍: Signal Processing incorporates all aspects of the theory and practice of signal processing. It features original research work, tutorial and review articles, and accounts of practical developments. It is intended for a rapid dissemination of knowledge and experience to engineers and scientists working in the research, development or practical application of signal processing. Subject areas covered by the journal include: Signal Theory; Stochastic Processes; Detection and Estimation; Spectral Analysis; Filtering; Signal Processing Systems; Software Developments; Image Processing; Pattern Recognition; Optical Signal Processing; Digital Signal Processing; Multi-dimensional Signal Processing; Communication Signal Processing; Biomedical Signal Processing; Geophysical and Astrophysical Signal Processing; Earth Resources Signal Processing; Acoustic and Vibration Signal Processing; Data Processing; Remote Sensing; Signal Processing Technology; Radar Signal Processing; Sonar Signal Processing; Industrial Applications; New Applications.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信