A lightweight skip-connected expansion inception network for remote sensing scene classification
Remote sensing image (RSI) scene classification is a hot topic in the field of remote sensing and has garnered a lot of attention. The key issue in image classification is effectively understanding semantic content. Convolutional neural networks (CNNs) are generally recognized to significantly impro...
Saved in:
Published in | Remote sensing letters Vol. 14; no. 10; pp. 1098 - 1108 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Abingdon
Taylor & Francis
03.10.2023
Taylor & Francis Ltd |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Remote sensing image (RSI) scene classification is a hot topic in the field of remote sensing and has garnered a lot of attention. The key issue in image classification is effectively understanding semantic content. Convolutional neural networks (CNNs) are generally recognized to significantly improve classification performance due to their powerful feature extraction capabilities. However, the overall structure of the model is complicated and has a large number of parameters, making it difficult to extract more efficient features. To address these problems, in this paper, we propose a lightweight skip-connected expansion Inception network called SEINet. To capture characteristics at a more granular level, we create a new lightweight backbone network with fewer parameters based on the existing network architecture. Additionally, the paper introduces a skip-connected expansion Inception (SEI) module for extracting context-dependent relationships. The ablation experiments verify the effectiveness of our proposed module. Experiment findings on two public datasets demonstrate that our method has advantages in classification accuracy and execution efficiency over state-of-the-art (SOTA) methods. |
---|---|
AbstractList | Remote sensing image (RSI) scene classification is a hot topic in the field of remote sensing and has garnered a lot of attention. The key issue in image classification is effectively understanding semantic content. Convolutional neural networks (CNNs) are generally recognized to significantly improve classification performance due to their powerful feature extraction capabilities. However, the overall structure of the model is complicated and has a large number of parameters, making it difficult to extract more efficient features. To address these problems, in this paper, we propose a lightweight skip-connected expansion Inception network called SEINet. To capture characteristics at a more granular level, we create a new lightweight backbone network with fewer parameters based on the existing network architecture. Additionally, the paper introduces a skip-connected expansion Inception (SEI) module for extracting context-dependent relationships. The ablation experiments verify the effectiveness of our proposed module. Experiment findings on two public datasets demonstrate that our method has advantages in classification accuracy and execution efficiency over state-of-the-art (SOTA) methods. |
Author | Li, Ziqi Wang, Xin Shi, Aiye |
Author_xml | – sequence: 1 givenname: Aiye orcidid: 0000-0001-8191-4346 surname: Shi fullname: Shi, Aiye email: ayshi@hhu.edu.cn organization: Hohai University – sequence: 2 givenname: Ziqi surname: Li fullname: Li, Ziqi organization: Hohai University – sequence: 3 givenname: Xin surname: Wang fullname: Wang, Xin organization: Hohai University |
BookMark | eNp9kEtLAzEUhYNUsNb-BCHgemoyeUxmZym-oOBGobuYZu7U6DQZkynaf-8MrS7NIjmEc87lfudo5IMHhC4pmVGiyHVOBSkIX81ykrNZnktJqTpB4-E_K4hQoz_NV2domtI76Q-jXBVqjF7nuHGbt-4LhhunD9dmNngPtoMKw3drfHLBY-cttN2gPHRfIX7gOkQcYRs6wAl6k9_gZMEDto1JydXOmsF_gU5r0ySYHt8Jerm7fV48ZMun-8fFfJlZxlSXldwUOVWMQbnmEmwlpAAjKqgVJ4aVwFQOtldWVnZdSlXKohSSGimMELxmE3R16G1j-NxB6vR72EXfj9S5UowP3bx3iYPLxpBShFq30W1N3GtK9MBT__LUA0995Nnnbg455_u9t6Yn0FS6M_smxDoab13S7P-KH6MIf4k |
CitedBy_id | crossref_primary_10_4108_eetinis_v11i3_4748 |
Cites_doi | 10.1016/j.patcog.2016.07.001 10.1109/JPROC.2017.2675998 10.3390/rs9030225 10.1109/JSTARS.2017.2761800 10.1109/JSTARS.2019.2919317 10.1109/TGRS.2021.3097938 10.1109/TGRS.2017.2685945 10.1109/TGRS.2015.2488681 10.1109/CVPR.2018.00716 10.3390/rs71114680 10.1080/2150704X.2016.1235299 10.1109/LGRS.2021.3078518 10.1109/TPAMI.2017.2699184 10.1038/nature14539 10.1109/TGRS.2020.3048024 10.1007/978-3-030-01264-9_8 10.1109/JSTARS.2020.3005403 10.3390/rs10050719 10.1109/ICCV.2017.74 10.1109/CVPR.2018.00474 |
ContentType | Journal Article |
Copyright | 2023 Informa UK Limited, trading as Taylor & Francis Group 2023 2023 Informa UK Limited, trading as Taylor & Francis Group |
Copyright_xml | – notice: 2023 Informa UK Limited, trading as Taylor & Francis Group 2023 – notice: 2023 Informa UK Limited, trading as Taylor & Francis Group |
DBID | AAYXX CITATION 7TN 8FD F1W FR3 H8D H96 KR7 L.G L7M |
DOI | 10.1080/2150704X.2023.2266118 |
DatabaseName | CrossRef Oceanic Abstracts Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace |
DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Oceanic Abstracts Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace |
DatabaseTitleList | Aerospace Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Geography |
EISSN | 2150-7058 |
EndPage | 1108 |
ExternalDocumentID | 10_1080_2150704X_2023_2266118 2266118 |
Genre | Research Letter |
GroupedDBID | .7F 0BK 0R~ 2DF 30N 3YN 4.4 AAAVI AAJMT AALDU AAMIU AAPUL AAQRR ABCCY ABFIM ABJVF ABLIJ ABPEM ABPTK ABQHQ ABRLO ABTAI ABXUL ABXYU ACGFO ACGFS ACIWK ACTIO ADCVX ADGTB ADMSI AEGYZ AEISY AENEX AEYOC AFOLD AFRAH AFWLO AGDLA AHDLD AHDSZ AIJEM AIRXU AKBVH AKOOK ALMA_UNASSIGNED_HOLDINGS ALQZU AQRUH AVBZW BLEHA CCCUG CE4 DKSSO EBS FUNRP FVPDL GTTXZ HZ~ IPNFZ J~4 KYCEM LJTGL M4Z O9- P2P PQQKQ RIG RNANH ROSJB RTWRZ SNACF TEN TFL TFT TFW TQWBC TTHFI UU3 V1K ZGOLN AAHBH AAYXX ABJNI ABPAQ AHDZW AWYRJ CITATION DGEBU H13 TBQAZ TDBHL TUROJ 7TN 8FD F1W FR3 H8D H96 KR7 L.G L7M |
ID | FETCH-LOGICAL-c338t-94a721833e9b46ecd565ea5def840a39e382ec0a3c6dcb9689679561a65a554f3 |
ISSN | 2150-704X |
IngestDate | Fri Sep 13 10:50:12 EDT 2024 Fri Aug 23 03:07:48 EDT 2024 Wed Nov 01 04:21:35 EDT 2023 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 10 |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c338t-94a721833e9b46ecd565ea5def840a39e382ec0a3c6dcb9689679561a65a554f3 |
ORCID | 0000-0001-8191-4346 |
PQID | 2883418334 |
PQPubID | 436422 |
PageCount | 11 |
ParticipantIDs | proquest_journals_2883418334 informaworld_taylorfrancis_310_1080_2150704X_2023_2266118 crossref_primary_10_1080_2150704X_2023_2266118 |
PublicationCentury | 2000 |
PublicationDate | 2023-10-03 |
PublicationDateYYYYMMDD | 2023-10-03 |
PublicationDate_xml | – month: 10 year: 2023 text: 2023-10-03 day: 03 |
PublicationDecade | 2020 |
PublicationPlace | Abingdon |
PublicationPlace_xml | – name: Abingdon |
PublicationTitle | Remote sensing letters |
PublicationYear | 2023 |
Publisher | Taylor & Francis Taylor & Francis Ltd |
Publisher_xml | – name: Taylor & Francis – name: Taylor & Francis Ltd |
References | e_1_3_2_16_1 e_1_3_2_9_1 e_1_3_2_17_1 e_1_3_2_8_1 e_1_3_2_7_1 e_1_3_2_19_1 e_1_3_2_2_1 e_1_3_2_20_1 e_1_3_2_10_1 e_1_3_2_21_1 e_1_3_2_11_1 Yu F. (e_1_3_2_18_1) 2016 e_1_3_2_22_1 e_1_3_2_6_1 e_1_3_2_12_1 e_1_3_2_5_1 e_1_3_2_13_1 e_1_3_2_4_1 e_1_3_2_14_1 e_1_3_2_3_1 e_1_3_2_15_1 |
References_xml | – ident: e_1_3_2_12_1 doi: 10.1016/j.patcog.2016.07.001 – ident: e_1_3_2_4_1 doi: 10.1109/JPROC.2017.2675998 – ident: e_1_3_2_15_1 doi: 10.3390/rs9030225 – ident: e_1_3_2_10_1 doi: 10.1109/JSTARS.2017.2761800 – ident: e_1_3_2_20_1 doi: 10.1109/JSTARS.2019.2919317 – ident: e_1_3_2_3_1 doi: 10.1109/TGRS.2021.3097938 – ident: e_1_3_2_16_1 doi: 10.1109/TGRS.2017.2685945 – ident: e_1_3_2_19_1 doi: 10.1109/TGRS.2015.2488681 – ident: e_1_3_2_21_1 doi: 10.1109/CVPR.2018.00716 – ident: e_1_3_2_8_1 doi: 10.3390/rs71114680 – ident: e_1_3_2_22_1 doi: 10.1080/2150704X.2016.1235299 – ident: e_1_3_2_2_1 doi: 10.1109/LGRS.2021.3078518 – ident: e_1_3_2_6_1 doi: 10.1109/TPAMI.2017.2699184 – ident: e_1_3_2_9_1 doi: 10.1038/nature14539 – ident: e_1_3_2_17_1 doi: 10.1109/TGRS.2020.3048024 – ident: e_1_3_2_11_1 doi: 10.1007/978-3-030-01264-9_8 – volume-title: 2016 International Conference on Learning Representations year: 2016 ident: e_1_3_2_18_1 contributor: fullname: Yu F. – ident: e_1_3_2_5_1 doi: 10.1109/JSTARS.2020.3005403 – ident: e_1_3_2_7_1 doi: 10.3390/rs10050719 – ident: e_1_3_2_14_1 doi: 10.1109/ICCV.2017.74 – ident: e_1_3_2_13_1 doi: 10.1109/CVPR.2018.00474 |
SSID | ssj0000314878 |
Score | 2.3311577 |
Snippet | Remote sensing image (RSI) scene classification is a hot topic in the field of remote sensing and has garnered a lot of attention. The key issue in image... |
SourceID | proquest crossref informaworld |
SourceType | Aggregation Database Publisher |
StartPage | 1098 |
SubjectTerms | Ablation Artificial neural networks Classification Computer networks convolution neural network (CNN) Feature extraction Image classification Lightweight Modules Neural networks Parameters Remote sensing scene classification skip-connected expansion Inception |
Title | A lightweight skip-connected expansion inception network for remote sensing scene classification |
URI | https://www.tandfonline.com/doi/abs/10.1080/2150704X.2023.2266118 https://www.proquest.com/docview/2883418334/abstract/ |
Volume | 14 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lj9MwELZgOcAF8RQLC_KBW5SQ2s7rWKFdrVApB1Kp4mJSxxYVq7Jss1qWX8-M7biJtuJ1iSK3jRvP5_Fn65sZQl4LzZTm7SSuCs1jYQyLK6FEnBteqqyasCbFeOf38_x0Id4ts-VOEmSjS7pVon7ujSv5H6tCG9gVo2T_wbLhodAA92BfuIKF4fpXNp5GZ7i3vrLHm9H26_o8VihcUUgj9Q-Y6FsnZfTalWjjRN9WW3ihwUo62qKCHc8UFHi9SCGZRvXQzmB99u7x189sGFAg5B9tbeBour4OQJnZlk_r7-vdob1zLEuf7dsfNjAnW-MBHvWNuh8D8RG4LOAPaVykTnOZ6GGbS9AefK4YYisdeNBJ6qpS-9UYoxT2enonjcSHY38J_tmEIdvw7nyUWXv-QZ4sZjNZHy_r2-QOK6oMN-o8nYfzOEzjX9qFO7xEH_BVpm_29jOiMqNEtzcWdstW6gfkvt9m0KnDzENyS28ekbu-4v2X68fk85QOsEPH2KEBOzRgh3rsUOifOuxQDwZqsUPH2HlCFifH9dvT2FfbiBXnZQdTtCmQL3NdrUSuVQtUXzdZq00p0oZXmpdMK7hTeatWVV5WeYFR0U2eNcBJDX9KDjbfNvoZoUUONDozzLDGCAV7BM2MaQvYaTNVwJpySJJ-4OS5S6oiJz5XbT_SEkda-pE-JNVweGVncWgcBCX_w2-PeltIP3e3EmtsC3xZ8fz3H78g93bz4IgcdBeX-iXQ0G71yuLnFx4whTI |
link.rule.ids | 315,786,790,27957,27958,60241,61030 |
linkProvider | Taylor & Francis |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI5gHODCGzEYkAPXli1J0-Y4IaYBYycm7Ra61IEJVNDWicevJ-4DbSDEgVulKlUTO_Zn67NNyKkAZoAnLU-FwD1hLfOUMMKTlkcmUC0WN7He-aYvuwNxNQyGc7UwSKvEGNoWjSJyW42XG5PRFSXujCGKaYqhj7O_fYY-phUtkxXpHA5eTt7sf-VZsD17lBtkXOXhsqqQ57cvLbiohQamPwx27oU6G8RU_1-QTx79WTbyzce31o7_2-AmWS9BKm0XWrVFliDdJqvlvPSH9x1y16ZPGNW_5olVOn0cv3gGKTPGAVgKb87EYBaOjtOSNUPTgm5O3S7pBJx-AJ0idz69p9hPCqhBGI-8pVxVdsmgc3F73vXKWQ2ecUFu5gQch4i2OKiRkGASBxQhDhKwLoKMuQIeMTDuycjEjJSMlAyxpjaWQewQjeV7pJY-p7BPaCgdCAsssyy2wjiECczaJHRxGjOhs0h14lfi0S9FSw7dKjudVgen8eB0eXB1ouaFqLM8F2KLwSWa_7G2UUlcl7d7qnFCs8DNioN_fPqErHZvb3q6d9m_PiRr-CpnCfIGqWWTGRw5tJONjnN1_gQhn_KQ |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI5gSMCFN2IwIAeuLVuSpu1xAqbxmjgwabfQpg5MQ2XaOvH49cR9IB5CHLhVqhIlseN8tj7bhBwJYBp40nJCH7gjjGFOKLRwpOGB9sIWi5qY73zdk92-uBh4FZtwWtIq0Yc2RaGI3Fbj5R4npmLEHTMEMU0xcLH1t8vwiWkF82RBYssszOJo9j7CLFidPcjtMY5ycFiVx_PbTF9eqC_1S3_Y6_wR6qySuFp-wT0ZubMsdvXbt8qO_9rfGlkpISptFzq1TuYg3SBLZbf0h9dNctemj-jTP-dhVTodDceORsKMtvCVwos1MBiDo8O05MzQtCCbU7tJOgGrHUCnyJxP7ylWkwKqEcQjaylXlC3S75zdnnSdslODo62Lm1nxRj5iLQ5hLCToxMJEiLwEjPUfIx4CDxho-6VlouNQBqH0MaM2kl5k8Yzh26SWPqWwQ6gvLQTzDDMsMkJbfAnMmMS3XhrTvrVHdeJW0lHjoiCHapV1TquDU3hwqjy4Ogk_y1BleSTEFG1LFP9jbKMSuCrv9lRhf2aBmxW7_5j6kCzenHbU1Xnvco8s45-cIsgbpJZNZrBvoU4WH-TK_A5GTvE9 |
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=A+lightweight+skip-connected+expansion+inception+network+for+remote+sensing+scene+classification&rft.jtitle=Remote+sensing+letters&rft.au=Shi%2C+Aiye&rft.au=Li%2C+Ziqi&rft.au=Wang%2C+Xin&rft.date=2023-10-03&rft.pub=Taylor+%26+Francis+Ltd&rft.issn=2150-704X&rft.eissn=2150-7058&rft.volume=14&rft.issue=10&rft.spage=1098&rft.epage=1108&rft_id=info:doi/10.1080%2F2150704X.2023.2266118&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2150-704X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2150-704X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2150-704X&client=summon |