Spatial and Channel Aggregation Network for Lightweight Image Super-Resolution
Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging resolution through the use of rapid and lightweight network architectures. Existing SISR methodologies face the challenge of striking a balance betwee...
Saved in:
Published in | Sensors (Basel, Switzerland) Vol. 23; no. 19; p. 8213 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Switzerland
MDPI AG
01.10.2023
MDPI |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging resolution through the use of rapid and lightweight network architectures. Existing SISR methodologies face the challenge of striking a balance between performance and computational costs, which hinders the practical application of SISR methods. In response to this challenge, the present study introduces a lightweight network known as the Spatial and Channel Aggregation Network (SCAN), designed to excel in image super-resolution (SR) tasks. SCAN is the first SISR method to employ large-kernel convolutions combined with feature reduction operations. This design enables the network to focus more on challenging intermediate-level information extraction, leading to improved performance and efficiency of the network. Additionally, an innovative 9 × 9 large kernel convolution was introduced to further expand the receptive field. The proposed SCAN method outperforms state-of-the-art lightweight SISR methods on benchmark datasets with a 0.13 dB improvement in peak signal-to-noise ratio (PSNR) and a 0.0013 increase in structural similarity (SSIM). Moreover, on remote sensing datasets, SCAN achieves a 0.4 dB improvement in PSNR and a 0.0033 increase in SSIM. |
---|---|
AbstractList | Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging resolution through the use of rapid and lightweight network architectures. Existing SISR methodologies face the challenge of striking a balance between performance and computational costs, which hinders the practical application of SISR methods. In response to this challenge, the present study introduces a lightweight network known as the Spatial and Channel Aggregation Network (SCAN), designed to excel in image super-resolution (SR) tasks. SCAN is the first SISR method to employ large-kernel convolutions combined with feature reduction operations. This design enables the network to focus more on challenging intermediate-level information extraction, leading to improved performance and efficiency of the network. Additionally, an innovative 9 × 9 large kernel convolution was introduced to further expand the receptive field. The proposed SCAN method outperforms state-of-the-art lightweight SISR methods on benchmark datasets with a 0.13 dB improvement in peak signal-to-noise ratio (PSNR) and a 0.0013 increase in structural similarity (SSIM). Moreover, on remote sensing datasets, SCAN achieves a 0.4 dB improvement in PSNR and a 0.0033 increase in SSIM. Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging resolution through the use of rapid and lightweight network architectures. Existing SISR methodologies face the challenge of striking a balance between performance and computational costs, which hinders the practical application of SISR methods. In response to this challenge, the present study introduces a lightweight network known as the Spatial and Channel Aggregation Network (SCAN), designed to excel in image super-resolution (SR) tasks. SCAN is the first SISR method to employ large-kernel convolutions combined with feature reduction operations. This design enables the network to focus more on challenging intermediate-level information extraction, leading to improved performance and efficiency of the network. Additionally, an innovative 9 × 9 large kernel convolution was introduced to further expand the receptive field. The proposed SCAN method outperforms state-of-the-art lightweight SISR methods on benchmark datasets with a 0.13 dB improvement in peak signal-to-noise ratio (PSNR) and a 0.0013 increase in structural similarity (SSIM). Moreover, on remote sensing datasets, SCAN achieves a 0.4 dB improvement in PSNR and a 0.0033 increase in SSIM.Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging resolution through the use of rapid and lightweight network architectures. Existing SISR methodologies face the challenge of striking a balance between performance and computational costs, which hinders the practical application of SISR methods. In response to this challenge, the present study introduces a lightweight network known as the Spatial and Channel Aggregation Network (SCAN), designed to excel in image super-resolution (SR) tasks. SCAN is the first SISR method to employ large-kernel convolutions combined with feature reduction operations. This design enables the network to focus more on challenging intermediate-level information extraction, leading to improved performance and efficiency of the network. Additionally, an innovative 9 × 9 large kernel convolution was introduced to further expand the receptive field. The proposed SCAN method outperforms state-of-the-art lightweight SISR methods on benchmark datasets with a 0.13 dB improvement in peak signal-to-noise ratio (PSNR) and a 0.0013 increase in structural similarity (SSIM). Moreover, on remote sensing datasets, SCAN achieves a 0.4 dB improvement in PSNR and a 0.0033 increase in SSIM. |
Audience | Academic |
Author | Huang, Feng Zuo, Linze Wu, Xianyu |
AuthorAffiliation | College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; xwu@fzu.edu.cn (X.W.); linzezuo@gmail.com (L.Z.) |
AuthorAffiliation_xml | – name: College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; xwu@fzu.edu.cn (X.W.); linzezuo@gmail.com (L.Z.) |
Author_xml | – sequence: 1 givenname: Xianyu orcidid: 0000-0001-6005-7058 surname: Wu fullname: Wu, Xianyu organization: College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China – sequence: 2 givenname: Linze surname: Zuo fullname: Zuo, Linze organization: College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China – sequence: 3 givenname: Feng surname: Huang fullname: Huang, Feng organization: College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37837043$$D View this record in MEDLINE/PubMed |
BookMark | eNpdkluPEyEUxydmjXvRB7-AmcQXfZiVy1DgyTSNlybNmrj6TLgcptQpVGbGjd9exq7NriEB8ud3_pwD57I6iylCVb3E6JpSid4NhGIpCKZPqgvckrYRhKCzB_vz6nIYdggRSql4Vp1TLihHLb2obm4Pegy6r3V09WqrY4S-XnZdhq7oKdY3MN6l_KP2Kdeb0G3HO5jner3XHdS30wFy8xWG1E8z_rx66nU_wIv79ar6_vHDt9XnZvPl03q13DSWITk2jmJLS87MuyJgy4Fx5LATxAvppGQGMBfEGmEMIuANZtp6Yhj2BlCL6VW1Pvq6pHfqkMNe598q6aD-Cil3Sucx2B4UA8OkFo7ZUrEXSDqsTbtwjHluWueK1_uj12Eye3AW4ph1_8j08UkMW9WlXwojxhkSoji8uXfI6ecEw6j2YbDQ9zpCmgZFBOdUyHYxo6__Q3dpyrG81UwtFphwTgp1faQ6XSoI0adysS3DwT7Y8vk-FH1ZUEYkRrwEvD0G2JyGIYM_pY-RmntEnXqksK8e1nsi_zUF_QNnD7g2 |
CitedBy_id | crossref_primary_10_1038_s41598_024_59384_x |
Cites_doi | 10.1007/978-3-030-67070-2_2 10.1109/ISCA52012.2021.00011 10.1016/j.neunet.2017.12.012 10.1007/978-3-319-10593-2_13 10.1109/TCSVT.2023.3271131 10.1016/j.patcog.2020.107475 10.1007/s41095-023-0364-2 10.1109/CVPR.2017.19 10.1007/s41095-022-0274-8 10.1007/978-3-319-46475-6_25 10.1109/ICCV.2015.123 10.1007/978-3-030-58598-3_7 10.1109/CVPR.2017.633 10.1109/CVPRW.2018.00132 10.1109/CVPR.2016.182 10.1109/TCSVT.2021.3138431 10.1609/aaai.v34i07.6877 10.1109/CVPR.2018.00418 10.1109/CVPR.2018.00745 10.1109/CVPR.2015.7299156 10.1109/CVPRW.2017.151 10.1007/978-3-030-01249-6_16 10.1109/TIP.2023.3242589 10.1109/CVPR52688.2022.01166 10.1109/CVPR46437.2021.01212 10.1109/TCYB.2019.2952710 10.1145/3474085.3475291 10.1109/ICCV48922.2021.00986 10.1007/978-3-030-01261-8_13 10.1109/CVPR52688.2022.01055 10.1109/CVPRW.2017.150 10.1109/CVPR.2017.243 10.1109/TCSVT.2022.3230824 10.1109/ICPR48806.2021.9413080 10.1007/978-3-030-01234-2_18 10.1109/CVPR46437.2021.00908 10.1016/j.isprsjprs.2019.11.023 10.1109/CVPRW56347.2022.00061 10.1109/CVPR46437.2021.01352 10.1109/TCSVT.2021.3078436 10.1007/978-3-030-58542-6_17 10.1145/3343031.3351084 10.5244/C.26.135 10.1109/TCSVT.2023.3250657 10.1109/CVPR.2016.90 10.1109/CVPR.2016.181 10.1007/s11042-016-4020-z 10.1109/WACV.2016.7477613 10.1109/ICCV.2017.514 10.1016/j.jvcir.2021.103300 10.1109/CVPR.2016.207 10.1109/CVPR.2019.01132 10.1109/CVPR.2018.00082 10.1002/adom.202300910 10.1109/ICCVW54120.2021.00210 |
ContentType | Journal Article |
Copyright | COPYRIGHT 2023 MDPI AG 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023 by the authors. 2023 |
Copyright_xml | – notice: COPYRIGHT 2023 MDPI AG – notice: 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023 by the authors. 2023 |
DBID | NPM AAYXX CITATION 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PIMPY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
DOI | 10.3390/s23198213 |
DatabaseName | PubMed CrossRef ProQuest Central (Corporate) ProQuest Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central ProQuest One Community College ProQuest Central Korea Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) Medical Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
DatabaseTitle | PubMed CrossRef Publicly Available Content Database ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Central China ProQuest Hospital Collection (Alumni) ProQuest Central ProQuest Health & Medical Complete Health Research Premium Collection ProQuest Medical Library ProQuest One Academic UKI Edition Health and Medicine Complete (Alumni Edition) ProQuest Central Korea ProQuest One Academic ProQuest Medical Library (Alumni) ProQuest Central (Alumni) MEDLINE - Academic |
DatabaseTitleList | Publicly Available Content Database PubMed CrossRef MEDLINE - Academic |
Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X7 name: ProQuest_Health & Medical Collection url: https://search.proquest.com/healthcomplete sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Architecture |
EISSN | 1424-8220 |
ExternalDocumentID | oai_doaj_org_article_5eb59a8d5c704f809d1ab46d55f7b4dd A772529107 10_3390_s23198213 37837043 |
Genre | Journal Article |
GeographicLocations | Germany |
GeographicLocations_xml | – name: Germany |
GrantInformation_xml | – fundername: Natural Science Foundation of Fujian Province of China grantid: No. 2023J01130137 – fundername: Fuzhou University grantid: GXRC-18066 – fundername: Natural Science Foundation of Fujian Province of China grantid: 2023J01130137 |
GroupedDBID | --- 123 2WC 3V. 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH ABDBF ABJCF ABUWG ADBBV AENEX AFKRA AFZYC ALIPV ALMA_UNASSIGNED_HOLDINGS ARAPS BENPR BPHCQ BVXVI CCPQU CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE IAO ITC KB. KQ8 L6V M1P M48 M7S MODMG M~E NPM OK1 P2P P62 PDBOC PIMPY PQQKQ PROAC PSQYO RIG RNS RPM TUS UKHRP XSB ~8M AAYXX CITATION BGLVJ 7XB 8FK AZQEC DWQXO K9. PQEST PQUKI PRINS 7X8 5PM |
ID | FETCH-LOGICAL-c509t-d31c33195fdc501c7e570d1d82f89d995be1782cb8bb02efb15acf2b51fbe0413 |
IEDL.DBID | RPM |
ISSN | 1424-8220 |
IngestDate | Tue Oct 22 15:15:40 EDT 2024 Tue Sep 17 21:29:29 EDT 2024 Fri Sep 27 03:04:40 EDT 2024 Thu Oct 10 20:15:51 EDT 2024 Fri Feb 02 04:39:54 EST 2024 Thu Sep 26 16:15:50 EDT 2024 Wed Oct 23 10:10:17 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 19 |
Keywords | large kernel convolution lightweight image super-resolution peak signal-to-noise ratio (PSNR) metric |
Language | English |
License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c509t-d31c33195fdc501c7e570d1d82f89d995be1782cb8bb02efb15acf2b51fbe0413 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0001-6005-7058 |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10575088/ |
PMID | 37837043 |
PQID | 2876612772 |
PQPubID | 2032333 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_5eb59a8d5c704f809d1ab46d55f7b4dd pubmedcentral_primary_oai_pubmedcentral_nih_gov_10575088 proquest_miscellaneous_2877389468 proquest_journals_2876612772 gale_infotracacademiconefile_A772529107 crossref_primary_10_3390_s23198213 pubmed_primary_37837043 |
PublicationCentury | 2000 |
PublicationDate | 2023-10-01 |
PublicationDateYYYYMMDD | 2023-10-01 |
PublicationDate_xml | – month: 10 year: 2023 text: 2023-10-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Switzerland |
PublicationPlace_xml | – name: Switzerland – name: Basel |
PublicationTitle | Sensors (Basel, Switzerland) |
PublicationTitleAlternate | Sensors (Basel) |
PublicationYear | 2023 |
Publisher | MDPI AG MDPI |
Publisher_xml | – name: MDPI AG – name: MDPI |
References | ref_50 Sun (ref_56) 2022; 35 Elfwing (ref_60) 2018; 107 Huang (ref_32) 2022; 33 Wang (ref_42) 2021; 80 ref_14 ref_58 ref_13 ref_57 ref_12 ref_11 ref_55 ref_10 ref_54 ref_52 ref_51 Wang (ref_63) 2022; 8 Imran (ref_18) 2023; 2023 ref_19 ref_17 ref_16 ref_15 ref_59 ref_61 ref_25 ref_69 ref_24 ref_23 ref_67 ref_22 ref_66 ref_21 ref_65 ref_20 ref_64 ref_62 Li (ref_53) 2020; 33 ref_29 ref_28 Liu (ref_31) 2021; 32 ref_26 Zhu (ref_35) 2021; 32 Jiang (ref_9) 2020; 107 ref_72 ref_70 Raghu (ref_37) 2021; 34 ref_34 ref_33 Lan (ref_7) 2020; 51 ref_30 ref_74 ref_73 ref_38 Tolstikhin (ref_36) 2021; 34 ref_47 ref_46 ref_45 ref_44 ref_43 ref_41 ref_40 ref_1 Huang (ref_27) 2023; 32 Matsui (ref_68) 2017; 76 ref_3 ref_2 Li (ref_71) 2020; 159 ref_49 ref_48 ref_8 ref_5 ref_4 Guo (ref_39) 2023; 9 ref_6 |
References_xml | – ident: ref_24 doi: 10.1007/978-3-030-67070-2_2 – ident: ref_19 doi: 10.1109/ISCA52012.2021.00011 – volume: 107 start-page: 3 year: 2018 ident: ref_60 article-title: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning publication-title: Neural Netw. doi: 10.1016/j.neunet.2017.12.012 contributor: fullname: Elfwing – ident: ref_4 doi: 10.1007/978-3-319-10593-2_13 – ident: ref_14 doi: 10.1109/TCSVT.2023.3271131 – volume: 107 start-page: 107475 year: 2020 ident: ref_9 article-title: Hierarchical dense recursive network for image super-resolution publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107475 contributor: fullname: Jiang – volume: 9 start-page: 733 year: 2023 ident: ref_39 article-title: Visual attention network publication-title: Comput. Vis. Media doi: 10.1007/s41095-023-0364-2 contributor: fullname: Guo – ident: ref_49 doi: 10.1109/CVPR.2017.19 – volume: 8 start-page: 415 year: 2022 ident: ref_63 article-title: Pvt v2: Improved baselines with pyramid vision transformer publication-title: Comput. Vis. Media doi: 10.1007/s41095-022-0274-8 contributor: fullname: Wang – ident: ref_65 – ident: ref_20 doi: 10.1007/978-3-319-46475-6_25 – ident: ref_74 doi: 10.1109/ICCV.2015.123 – ident: ref_10 doi: 10.1007/978-3-030-58598-3_7 – ident: ref_61 – ident: ref_28 doi: 10.1109/CVPR.2017.633 – ident: ref_3 doi: 10.1109/CVPRW.2018.00132 – ident: ref_5 doi: 10.1109/CVPR.2016.182 – volume: 32 start-page: 4927 year: 2021 ident: ref_31 article-title: Cross-SRN: Structure-preserving super-resolution network with cross convolution publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2021.3138431 contributor: fullname: Liu – ident: ref_26 doi: 10.1609/aaai.v34i07.6877 – ident: ref_58 – ident: ref_72 doi: 10.1109/CVPR.2018.00418 – ident: ref_69 – ident: ref_15 doi: 10.1109/CVPR.2018.00745 – ident: ref_41 – volume: 33 start-page: 20343 year: 2020 ident: ref_53 article-title: Lapar: Linearly-assembled pixel-adaptive regression network for single image super-resolution and beyond publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: Li – ident: ref_66 – volume: 35 start-page: 17314 year: 2022 ident: ref_56 article-title: ShuffleMixer: An Efficient ConvNet for Image Super-Resolution publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: Sun – ident: ref_67 doi: 10.1109/CVPR.2015.7299156 – ident: ref_6 doi: 10.1109/CVPRW.2017.151 – ident: ref_21 doi: 10.1007/978-3-030-01249-6_16 – volume: 32 start-page: 1257 year: 2023 ident: ref_27 article-title: Spectral Clustering Super-Resolution Imaging Based on Multispectral Camera Array publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2023.3242589 contributor: fullname: Huang – ident: ref_59 – ident: ref_38 doi: 10.1109/CVPR52688.2022.01166 – ident: ref_51 doi: 10.1109/CVPR46437.2021.01212 – volume: 51 start-page: 115 year: 2020 ident: ref_7 article-title: Cascading and enhanced residual networks for accurate single-image super-resolution publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2019.2952710 contributor: fullname: Lan – ident: ref_25 doi: 10.1145/3474085.3475291 – ident: ref_62 doi: 10.1109/ICCV48922.2021.00986 – ident: ref_30 – ident: ref_2 doi: 10.1007/978-3-030-01261-8_13 – ident: ref_40 doi: 10.1109/CVPR52688.2022.01055 – ident: ref_64 doi: 10.1109/CVPRW.2017.150 – ident: ref_13 doi: 10.1109/CVPR.2017.243 – volume: 33 start-page: 2672 year: 2022 ident: ref_32 article-title: Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2022.3230824 contributor: fullname: Huang – ident: ref_33 doi: 10.1109/ICPR48806.2021.9413080 – ident: ref_44 – ident: ref_11 doi: 10.1007/978-3-030-01234-2_18 – ident: ref_46 doi: 10.1109/CVPR46437.2021.00908 – volume: 159 start-page: 296 year: 2020 ident: ref_71 article-title: Object detection in optical remote sensing images: A survey and a new benchmark publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2019.11.023 contributor: fullname: Li – ident: ref_55 doi: 10.1109/CVPRW56347.2022.00061 – ident: ref_73 – ident: ref_34 doi: 10.1109/CVPR46437.2021.01352 – volume: 32 start-page: 1273 year: 2021 ident: ref_35 article-title: Lightweight image super-resolution with expectation-maximization attention mechanism publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2021.3078436 contributor: fullname: Zhu – ident: ref_54 doi: 10.1007/978-3-030-58542-6_17 – ident: ref_23 doi: 10.1145/3343031.3351084 – volume: 34 start-page: 12116 year: 2021 ident: ref_37 article-title: Do vision transformers see like convolutional neural networks? publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: Raghu – ident: ref_47 doi: 10.5244/C.26.135 – ident: ref_50 – ident: ref_17 doi: 10.1109/TCSVT.2023.3250657 – ident: ref_29 – ident: ref_12 doi: 10.1109/CVPR.2016.90 – volume: 34 start-page: 24261 year: 2021 ident: ref_36 article-title: Mlp-mixer: An all-mlp architecture for vision publication-title: Adv. Neural Inf. Process. Syst. contributor: fullname: Tolstikhin – ident: ref_48 doi: 10.1109/CVPR.2016.181 – volume: 76 start-page: 21811 year: 2017 ident: ref_68 article-title: Sketch-based Manga Retrieval using Manga109 Dataset publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-016-4020-z contributor: fullname: Matsui – ident: ref_1 doi: 10.1109/WACV.2016.7477613 – ident: ref_8 doi: 10.1109/ICCV.2017.514 – volume: 80 start-page: 103300 year: 2021 ident: ref_42 article-title: Multi-scale attention network for image super-resolution publication-title: J. Vis. Commun. Image Represent. doi: 10.1016/j.jvcir.2021.103300 contributor: fullname: Wang – ident: ref_70 – ident: ref_43 – ident: ref_52 doi: 10.1109/CVPR.2016.207 – ident: ref_16 doi: 10.1109/CVPR.2019.01132 – ident: ref_22 doi: 10.1109/CVPR.2018.00082 – volume: 2023 start-page: 2300910 year: 2023 ident: ref_18 article-title: Electric-Dipole Gated Two Terminal Phototransistor for Charge-Coupled Device publication-title: Adv. Opt. Mater. doi: 10.1002/adom.202300910 contributor: fullname: Imran – ident: ref_57 – ident: ref_45 doi: 10.1109/ICCVW54120.2021.00210 |
SSID | ssj0023338 |
Score | 2.455645 |
Snippet | Advanced deep learning-based Single Image Super-Resolution (SISR) techniques are designed to restore high-frequency image details and enhance imaging... |
SourceID | doaj pubmedcentral proquest gale crossref pubmed |
SourceType | Open Website Open Access Repository Aggregation Database Index Database |
StartPage | 8213 |
SubjectTerms | Algorithms Architecture Deep learning large kernel convolution lightweight image super-resolution Neural networks peak signal-to-noise ratio (PSNR) metric Remote sensing |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NbxUhFCVNV3Zh_Kg6tRpsmriadGBgmFlWY1NN-za1SXeEz-rCadO-F_--B5j38iYu3LgFJoF7gXsOA-cScgwIzZs2ALkhttaiFaZGUOjqqHgQ3qnO5Mxzl4vu_Fp8u5E3W6m-0p2wIg9cDHcig5WD6b10qhGxbwbPjBWdlzIqK7zPuy-TazI1Ua0WzKvoCLUg9SePQDFDz1k7iz5ZpP_vrXgrFs3vSW4FnrNn5OmEGOlp6elzshPGF2RvS0fwJVmkxMKYSNSMnqb3AmPAB7eg0rfZ8HRRLntTIFR6kej473wiSr_-wnZCr1b34aFOB_llGu6T67Mv3z-f11OihNoh3i9r3zLXYoQyehQwp4JUjWe-57Ef_DBIGxiQgLO9tQ0P0TJpXORWsmhDgzD2iuyOd2N4Q6gC_0BpZJ0DUTRxsIJb5g3WteuCsBU5WhtQ3xc9DA0ekaysN1auyKdk2k2DJGGdC-BYPTlW_8uxFfmYHKPTQoP1nZneC6CfSbJKn4IXSA60oypyuPadnlbgowYTBPTgaFSRD5tqrJ30Q8SM4W6V2ygANtH1FXldXL3pc6uSLJDAWPrZJJgNal4z_vyR9blT6uSEew_-hxnekicpw325P3hIdpcPq_AOOGhp3-cp_wf9pAfD priority: 102 providerName: Directory of Open Access Journals – databaseName: ProQuest Technology Collection dbid: 8FG link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lj9QwDLZguQASguVVWFBBSJyqbdKkaU9oQAwLgrnASnuL8hw40BnmIf4-dtopUyFxTVopie34c-J8BniFEJqXVUDkhr61EJUwBTqFuoiKB-Gdqk2qPPdlUV9cik9X8mo4cNsOaZWHPTFt1H7l6Iz8HJE9uhKOYPDN-ldBVaPodnUooXEdbjBiwqOX4vMPY8BVYfzVswlVGNqfbxHLtA1n1cQHJar-fzfkI480zZY8cj_zu3BnwI35rBf0PbgWulO4PTu6BjiFW0fkgvdhQdWGUbty0_mcHhF0Af9fYny9TNLIF30GeI6wNf9MMfrvdEyaf_yJe0z-db8Om4JO93vdfACX8_ff3l0UQ_WEwiEI2BW-Yq7CCcvosYE5FaQqPfMNj03r21bawBAeONtYW_IQLZPGRW4lizaU6Nsewkm36sJjyBUGJdgaWe0wejSxtYJb5g0au6uDsBm8PKynXvckGRqDC1p0PS56Bm9ppccPiNc6Naw2Sz2YiZbBytY0XjpVitiUrWfGitpLGZUV3mfwmuSkyfpQGM4MjwhwnMRjpWeoH5IjBFIZnB1EqQez3Oq_SpTBi7EbDYpuSUwXVvv0jUIUJ-omg0e95McxV4q4ggTOpZnoxGRS057ux_dE2k31lAkMP_n_uJ7CTSpo36cLnsHJbrMPzxD27OzzpNt_ADgcA2Y priority: 102 providerName: ProQuest – databaseName: Scholars Portal Journals: Open Access dbid: M48 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Nb9QwEB1V7QUOiG8CLTIIiVMgcew4OVRVQVQF0b3ASr1Z_lyQIFu2uwL-PTNONtoIDlwdR4lnxpn3HHsewAuE0LyoAiI3zK25qITJMSnUeVQ8CO9UbZLy3MWsPp-LD5fycg-2GpuDAa__Se1IT2q--vbq14_fJzjhj4lxImV_fY0YpW04adcecHwcBfqFGH8m8KpKgtZ0pivHfFj0BYamt07SUqre__c3eidJTTdQ7mSks9twa4CS7LT3_R3YC91duLlTYPAezEhxGCOMmc4zOkjQBbxhgRx7kTzCZv0ucIbQlX0knv4zLZWy99_xO8M-ba7CKqcV_j4-78P87N3nt-f5oKCQOwQC69xXpatwhDJ6bCidClIVvvQNj03r21baUCJEcLaxtuAh2lIaF7mVZbShwPz2APa7ZRceAVNITLA1lrVDBmliawW3pTc44V0dhM3g-daA-qovlKGRYJCV9WjlDN6QaccOVNs6NSxXCz1MFS2Dla1pvHSqELEpWl8aK2ovZVRWeJ_BS3KMpphA6zszHCTA96RaVvoUCYPkCINUBodb3-ltZGmkiIhJOHbK4Nl4GScV_SkxXVhuUh-FSE7UTQYPe1eP71wpqhckcCzNJAgmg5pe6b5-SYW7SVOZAPHj_x7BE7hB-vb97sFD2F-vNuEIUdDaPk0x_gdEcgW7 priority: 102 providerName: Scholars Portal |
Title | Spatial and Channel Aggregation Network for Lightweight Image Super-Resolution |
URI | https://www.ncbi.nlm.nih.gov/pubmed/37837043 https://www.proquest.com/docview/2876612772 https://www.proquest.com/docview/2877389468/abstract/ https://pubmed.ncbi.nlm.nih.gov/PMC10575088 https://doaj.org/article/5eb59a8d5c704f809d1ab46d55f7b4dd |
Volume | 23 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Nb9MwFH_axgUOiG8CowoIiVPWOLZj57hNKwPRagIm9Rb5s0yiadW14t_n2UmqRty45OA4kvM-8n4_5_k9gI8IoYucOkRuGFszRpnKMCiUmReFY9aIUsXOc9NZeX3Lvs75_AjK_ixMTNo3-u6s-b08a-5-xdzK9dKM-zyx8c30MvSmDcBifAzHgtKeo3c0iyLramsIUST043tEMJUsSOiYQ0Wo9cLoIAjFWv3_fpEPQtIwXfIg_kyewOMOOKbn7QKfwpFrnsGjg3KCz2EW-gujPaWqsWk4NtA4fGCBjHoR5Z_O2pzvFIFq-i2w8j9xYzT9ssSvSvpjt3abLOznt9b4Am4nVz8vr7OuX0JmMOxvM0uJofiy3FscIEY4LnJLrCy8rGxVce0IAgKjpdZ54bwmXBlfaE68djlGs5dw0qwa9xpSgTQERz0pDfJF5SvNCk2sQvc2pWM6gQ-9AOt1WxajRjoRBF7vBZ7ARRDtfkKoZB0HVptF3emz5k7zSknLDSrGy7yyRGlWWs690MzaBD4FxdTB31D6RnXHBnCdoXJVfY70gBcIekQCp73u6s4R72skhIhACpyUwPv9bXSh8F9ENW61i3ME4jZWygRetarer7m3mATkwAgGLzW8g1Yby3T3Vvrm_x99Cw9De_s2efAUTrabnXuHIGirR2j5c4FXOfk8ggcXV7Ob76O4oYDXKZOj6BN_AZkvDO0 |
link.rule.ids | 230,315,733,786,790,870,891,2115,2236,12083,12792,21416,24346,27955,27956,31752,31753,33406,33407,33777,33778,43343,43633,43838,53825,53827,74100,74390,74657 |
linkProvider | National Library of Medicine |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwEB7B9sBDQlAoBAoEhMQpapzYcXJCW9RqC9sIQSv1Zvm5cCC77EP8fWaS7LIRElc7kWzPjOcbe_wNwDuE0Fmae0Ru6FsTnnOdoFMokiAzz52VhW4rz13WxeSaf7oRN_2B26pPq9zuie1G7eaWzshPENmjK8kQDH5Y_EqoahTdrvYlNG7DAVFuliM4OD2rv3zdhVw5RmAdn1COwf3JCtFMVWYsH3ihlqz_3y15zycN8yX3HND5Q3jQI8d43In6EdzyzSHcH-9dBBzCvT16wcdQU71h1K9YNy6mZwSNx_9nGGHPWnnEdZcDHiNwjacUpf9uD0rji5-4y8TfNgu_TOh8v9POJ3B9fnb1cZL09RMSizBgnbic2RwnLILDBmalFzJ1zJVZKCtXVcJ4hgDBmtKYNPPBMKFtyIxgwfgUvdsRjJp5459BLDEswdbACovxow6V4ZlhTqO528JzE8Hb7XqqRUeToTC8oEVXu0WP4JRWevcBMVu3DfPlTPWGooQ3otKlE1amPJRp5Zg2vHBCBGm4cxG8Jzkpsj8UhtX9MwIcJzFZqTFqiMgQBMkIjreiVL1hrtRfNYrgza4bTYruSXTj55v2G4k4jhdlBE87ye_GnEtiC-I4l3KgE4NJDXuaH99b2m6qqExw-Pn_x_Ua7kyuLqdqelF_fgF3qbx9lzx4DKP1cuNfIgham1e9pv8B9X4HvQ |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3di9QwEB_0BFFB9PS0emoVwaeyTZs07ZOsH8udnougB_sW8rn6YHfdD_z3nWmze1sEX5MWkvn8TTKZAXiNELrIS4_IDX1rxkuuM3QKVRZk4bmzstJd57kv0-rskn-aiVnMf1rHtMqdTewMtVtYOiMfIbJHV1IgGByFmBbx9cPk7fJ3Rh2k6KY1ttO4DjfQS-bUxkHOroKvEmOxvrJQiWH-aI24pqkLVg78UVe2_1_jfOCdhpmTB65ocg_uRgyZjnum34drvj2GO-ODK4FjuH1QaPABTKnzMEpaqluX0oOC1uP_c4y15x1n0mmfDZ4ihE0vKF7_0x2Zpue_0N6k37ZLv8ropL-X04dwOfn4_f1ZFjspZBYBwSZzJbMlblgEhwPMSi9k7piri1A3rmmE8QyhgjW1MXnhg2FC21AYwYLxOfq5EzhqF61_DKnEAAVHA6ssRpI6NIYXhjmNim8rz00Cr3b0VMu-YIbCQIOIrvZET-AdUXr_AdW47gYWq7mKKqOEN6LRtRNW5jzUeeOYNrxyQgRpuHMJvCE-KdJEZIbV8UEBrpNqWqkxyoooEA7JBE53rFRRRdfqSqASeLmfRuWiGxPd-sW2-0YiouNVncCjnvP7NZeS6gZx3Es9kInBpoYz7c8fXQFv6q1MwPjJ_9f1Am6iiKuL8-nnp3CL-tz3WYSncLRZbf0zREMb87wT87-Kigp6 |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Spatial+and+Channel+Aggregation+Network+for+Lightweight+Image+Super-Resolution&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Wu%2C+Xianyu&rft.au=Zuo%2C+Linze&rft.au=Huang%2C+Feng&rft.date=2023-10-01&rft.pub=MDPI+AG&rft.issn=1424-8220&rft.eissn=1424-8220&rft.volume=23&rft.issue=19&rft_id=info:doi/10.3390%2Fs23198213&rft.externalDocID=A772529107 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon |