{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:25:27Z","timestamp":1740104727641,"version":"3.37.3"},"reference-count":85,"publisher":"Wiley","license":[{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014959","name":"Guangxi Key Laboratory of Multi-Source Information Mining and Security","doi-asserted-by":"publisher","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}],"id":[{"id":"10.13039\/501100014959","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People\u2019s Republic of China","doi-asserted-by":"publisher","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Fund of Guangxi Key Laboratory of Machine Vision and Intelligent Control","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}]},{"name":"Open Foundation of Yunnan Key Laboratory of Software Engineering","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"],"award-info":[{"award-number":["62001316","61961036","24QYCX0399","MIMS22-14","TJUT-CVS20220001","2022B05","2023SE206","SCU2023D062","2021CDDZ-08-SCU","2022CDSN-15-SCU"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2024,2,15]]},"abstract":"<jats:p>In recent years, remarkable performance improvements have been produced by deep convolutional neural networks (CNN) for single image super-resolution (SISR). Nevertheless, a high proportion of CNN-based SISR models are with quite a few network parameters and high computational complexity for deep or wide architectures. How to more fully utilize deep features to make a balance between model complexity and reconstruction performance is one of the main challenges in this field. To address this problem, on the basis of the well-known information multi-distillation model, a multi-attention feature distillation network termed as MAFDN is developed for lightweight and accurate SISR. Specifically, an effective multi-attention feature distillation block (MAFDB) is designed and used as the basic feature extraction unit in MAFDN. With the help of multi-attention layers including pixel attention, spatial attention, and channel attention, MAFDB uses multiple information distillation branches to learn more discriminative and representative features. Furthermore, MAFDB introduces the depthwise over-parameterized convolutional layer (DO-Conv)-based residual block (OPCRB) to enhance its ability without incurring any parameter and computation increase in the inference stage. The results on commonly used datasets demonstrate that our MAFDN outperforms existing representative lightweight SISR models when taking both reconstruction performance and model complexity into consideration. For example, for <jats:inline-formula><a:math xmlns:a=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"M1\"><a:mo>\u00d7<\/a:mo><\/a:math><\/jats:inline-formula>4 SR on Set5, MAFDN (597K\/33.79G) obtains 0.21\u2009dB\/0.0037 and 0.10\u2009dB\/0.0015 PSNR\/SSIM gains over the attention-based SR model AFAN (692K\/50.90G) and the feature distillation-based SR model DDistill-SR (675K\/32.83G), respectively.<\/jats:p>","DOI":"10.1155\/2024\/3255233","type":"journal-article","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T23:27:56Z","timestamp":1708039676000},"page":"1-14","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Attention Feature Distillation Neural Network for Lightweight Single Image Super-Resolution"],"prefix":"10.1155","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9363-2056","authenticated-orcid":true,"given":"Yongfei","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China"},{"name":"Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin 541004, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2973-4599","authenticated-orcid":true,"given":"Xinying","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China"},{"name":"Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology, Tianjin 300384, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7731-230X","authenticated-orcid":true,"given":"Hong","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1733-9155","authenticated-orcid":true,"given":"Jie","family":"He","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Machine Vision and Intelligent Control, Wuzhou University, Wuzhou 543002, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-0005","authenticated-orcid":true,"given":"Linbo","family":"Qing","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8399-3172","authenticated-orcid":true,"given":"Xiaohai","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3097-8273","authenticated-orcid":true,"given":"Yi","family":"Li","sequence":"additional","affiliation":[{"name":"D.I. Sinma (Sichuan) Machinery Co., Ltd., Suining 629201, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6200-5147","authenticated-orcid":true,"given":"Honggang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China"},{"name":"Yunnan Key Laboratory of Software Engineering, Yunnan University, Kunming 650600, China"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.09.005"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3203009"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2022.3190350"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3006414"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2921882"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3258666"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312321"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2008.924279"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2012.2231086"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/tgcn.2021.3067555"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2017.2688920"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2018.02.031"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2012.2208977"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2012.2235847"},{"first-page":"711","article-title":"On single image scale-up using sparse-representations","author":"R. Zeyde","key":"15"},{"first-page":"111","article-title":"A+: adjusted anchored neighborhood regression for fast super-resolution","author":"R. Timofte","key":"16"},{"first-page":"71","article-title":"SRHRF+: self-example enhanced single image super-resolution using hierarchical random forests","author":"J.-J. Huang","key":"17"},{"first-page":"184","article-title":"Learning a deep convolutional network for image super-resolution","author":"C. Dong","key":"18"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2015.2439281"},{"first-page":"136","article-title":"Enhanced deep residual networks for single image super-resolution","author":"B. Lim","key":"20"},{"first-page":"286","article-title":"Image super-resolution using very deep residual channel attention networks","author":"Y. Zhang","key":"21"},{"first-page":"191","article-title":"Single image super-resolution via a holistic attention network","author":"B. Niu","key":"22"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229689"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3238524"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1002\/int.22691"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1002\/int.22956"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1002\/int.22505"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1002\/int.22551"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1002\/int.22333"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1002\/int.22822"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1002\/int.22499"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1002\/int.22627"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1002\/int.22806"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1002\/int.22687"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3107352"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1002\/int.22965"},{"first-page":"2024","article-title":"Lightweight image super-resolution with information multi-distillation network","author":"Z. Hui","key":"37"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19946"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3219646"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3134172"},{"first-page":"4395","article-title":"A lightweight local-global attention network for single image super-resolution","author":"Z. Song","key":"41"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2023.3304672"},{"key":"43","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.01.024"},{"first-page":"1646","article-title":"Accurate image super-resolution using very deep convolutional networks","author":"J. Kim","key":"44"},{"first-page":"2472","article-title":"Residual dense network for image super-resolution","author":"Y. Zhang","key":"45"},{"first-page":"11 065","article-title":"Second-order attention network for single image super-resolution","author":"T. Dai","key":"46"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3266222"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2022.3192280"},{"first-page":"1833","article-title":"SwinIR: image restoration using swin transformer","author":"J. Liang","key":"49"},{"first-page":"649","article-title":"Efficient long-range attention network for image super-resolution","author":"X. Zhang","key":"50"},{"first-page":"1637","article-title":"Deeply-recursive convolutional network for image super-resolution","author":"J. Kim","key":"51"},{"first-page":"3147","article-title":"Image super-resolution via deep recursive residual network","author":"Y. Tai","key":"52"},{"key":"53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107475"},{"first-page":"723","article-title":"Fast and accurate single image super-resolution via information distillation network","author":"Z. Hui","key":"54"},{"key":"55","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117594"},{"first-page":"1249","article-title":"Asymmetric information distillation network for lightweight super resolution","author":"Z. Zong","key":"56"},{"key":"57","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110437"},{"first-page":"41","article-title":"Residual feature distillation network for lightweight image super-resolution","author":"J. Liu","key":"58"},{"key":"59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108997"},{"key":"60","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3078436"},{"key":"61","doi-asserted-by":"publisher","DOI":"10.1145\/3546076"},{"key":"62","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103834"},{"key":"63","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-023-11213-4"},{"key":"64","doi-asserted-by":"publisher","DOI":"10.1145\/3569900"},{"key":"65","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2022.116898"},{"key":"66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25333"},{"first-page":"457","article-title":"Transformer for single image super-resolution","author":"Z. Lu","key":"67"},{"key":"68","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-03021-7"},{"first-page":"7852","article-title":"Data-free knowledge distillation for image super-resolution","author":"Y. Zhang","key":"69"},{"key":"70","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108909"},{"key":"71","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3230824"},{"key":"72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6877"},{"first-page":"1874","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","author":"W. Shi","key":"73"},{"first-page":"56","article-title":"Efficient image super-resolution using pixel attention","author":"H. Zhao","key":"74"},{"author":"J. Liu","key":"75","article-title":"Residual feature aggregation network for image super-resolution"},{"first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","author":"F. Chollet","key":"76"},{"first-page":"833","article-title":"Blueprint separable residual network for efficient image super-resolution","author":"Z. Li","key":"77"},{"key":"78","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2019.2915238"},{"key":"79","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3175432"},{"first-page":"126","article-title":"NTIRE 2017 challenge on single image super-resolution: dataset and study","author":"E. Agustsson","key":"80"},{"first-page":"114","article-title":"NTIRE 2017 challenge on single image super-resolution: methods and results","author":"R. Timofte","key":"81"},{"first-page":"1","article-title":"Low-complexity single-image super-resolution based on nonnegative neighbor embedding","author":"M. Bevilacqua","key":"82"},{"key":"83","first-page":"416","article-title":"A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics","volume":"2","author":"D. Martin","year":"2001","journal-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)"},{"first-page":"5197","article-title":"Single image super-resolution from transformed self-exemplars","author":"J.-B. Huang","key":"84"},{"first-page":"1","article-title":"Manga109 set and creation of metadata","author":"A. Fujimoto","key":"85"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2024\/3255233.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2024\/3255233.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2024\/3255233.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T23:28:07Z","timestamp":1708039687000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/ijis\/2024\/3255233\/"}},"subtitle":[],"editor":[{"given":"Mohammad R.","family":"Khosravi","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,2,15]]},"references-count":85,"alternative-id":["3255233","3255233"],"URL":"https:\/\/doi.org\/10.1155\/2024\/3255233","relation":{},"ISSN":["1098-111X","0884-8173"],"issn-type":[{"type":"electronic","value":"1098-111X"},{"type":"print","value":"0884-8173"}],"subject":[],"published":{"date-parts":[[2024,2,15]]}}}