Rethinking Transformers for Semantic Segmentation of Remote Sensing Images

Transformer has been widely applied in image processing tasks as a substitute for convolutional neural networks (CNNs) for feature extraction due to its superiority in global context modeling and flexibility in model generalization. However, the existing transformer-based methods for semantic segmen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on geoscience and remote sensing Ročník 61; s. 1 - 15
Hlavní autoři: Liu, Yuheng, Zhang, Yifan, Wang, Ye, Mei, Shaohui
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:0196-2892, 1558-0644
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Transformer has been widely applied in image processing tasks as a substitute for convolutional neural networks (CNNs) for feature extraction due to its superiority in global context modeling and flexibility in model generalization. However, the existing transformer-based methods for semantic segmentation of remote sensing (RS) images are still with several limitations, which can be summarized into two main aspects: 1) the transformer encoder is generally combined with CNN-based decoder, leading to inconsistency in feature representations; and 2) the strategies for global and local context information utilization are not sufficiently effective. Therefore, in this article, a global-local transformer segmentor (GLOTS) framework is proposed for the semantic segmentation of RS images to acquire consistent feature representations by adopting transformers for both encoding and decoding, in which a masked image modeling (MIM) pretrained transformer encoder is adopted to learn semantic-rich representations of input images and a multiscale global-local transformer decoder is designed to fully exploit the global and local features. Specifically, the transformer decoder uses a feature separation-aggregation module (FSAM) to utilize the feature adequately at different scales and adopts a global-local attention module (GLAM) containing global attention block (GAB) and local attention block (LAB) to capture the global and local context information, respectively. Furthermore, a learnable progressive upsampling strategy (LPUS) is proposed to restore the resolution progressively, which can flexibly recover the fine-grained details in the upsampling process. The experiment results on the three benchmark RS datasets demonstrate that the proposed GLOTS is capable of achieving better performance with some state-of-the-art methods, and the superiority of the proposed framework is also verified by ablation studies. The code will be available at https://github.com/lyhnsn/GLOTS .
AbstractList Transformer has been widely applied in image processing tasks as a substitute for convolutional neural networks (CNNs) for feature extraction due to its superiority in global context modeling and flexibility in model generalization. However, the existing transformer-based methods for semantic segmentation of remote sensing (RS) images are still with several limitations, which can be summarized into two main aspects: 1) the transformer encoder is generally combined with CNN-based decoder, leading to inconsistency in feature representations; and 2) the strategies for global and local context information utilization are not sufficiently effective. Therefore, in this article, a global-local transformer segmentor (GLOTS) framework is proposed for the semantic segmentation of RS images to acquire consistent feature representations by adopting transformers for both encoding and decoding, in which a masked image modeling (MIM) pretrained transformer encoder is adopted to learn semantic-rich representations of input images and a multiscale global-local transformer decoder is designed to fully exploit the global and local features. Specifically, the transformer decoder uses a feature separation-aggregation module (FSAM) to utilize the feature adequately at different scales and adopts a global-local attention module (GLAM) containing global attention block (GAB) and local attention block (LAB) to capture the global and local context information, respectively. Furthermore, a learnable progressive upsampling strategy (LPUS) is proposed to restore the resolution progressively, which can flexibly recover the fine-grained details in the upsampling process. The experiment results on the three benchmark RS datasets demonstrate that the proposed GLOTS is capable of achieving better performance with some state-of-the-art methods, and the superiority of the proposed framework is also verified by ablation studies. The code will be available at https://github.com/lyhnsn/GLOTS .
Author Liu, Yuheng
Wang, Ye
Zhang, Yifan
Mei, Shaohui
Author_xml – sequence: 1
  givenname: Yuheng
  orcidid: 0000-0001-5007-8533
  surname: Liu
  fullname: Liu, Yuheng
  email: hnlyh@mail.nwpu.edu.cn
  organization: School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China
– sequence: 2
  givenname: Yifan
  orcidid: 0000-0003-4533-3880
  surname: Zhang
  fullname: Zhang, Yifan
  email: yifanzhang@nwpu.edu.cn
  organization: School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China
– sequence: 3
  givenname: Ye
  orcidid: 0009-0009-5689-8271
  surname: Wang
  fullname: Wang, Ye
  email: wy2017263322@mail.nwpu.edu.cn
  organization: School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China
– sequence: 4
  givenname: Shaohui
  orcidid: 0000-0002-8018-596X
  surname: Mei
  fullname: Mei, Shaohui
  email: meish@nwpu.edu.cn
  organization: School of Electronics and Information, Northwestern Polytechnical University, Xi'an, China
BookMark eNp9kE9LAzEQxYNUsK1-AMHDguetmWT_5ShFa6UgtPW8ZLOTurWb1GR78NubZXsQD57eMDO_ecybkJGxBgm5BToDoOJhu1hvZowyPuOcBk0uyBjStIhpliQjMqYgspgVgl2Rifd7SiFJIR-T1zV2H435bMwu2jppvLauReejoNEGW2m6RoVi16LpZNdYE1kdrbG1HYa28T24bOUO_TW51PLg8easU_L-_LSdv8Srt8Vy_riKFRNJF1dUSAFK1UzTSle14olQteCoKMhaFyoRIi8qimmFqcoAFCrNeS7SDBTUKZ-S--Hu0dmvE_qu3NuTM8GyZEUKnPPwZtiCYUs5671DXR5d00r3XQIt-8jKPrKyj6w8RxaY_A-jmuHpzsnm8C95N5ANIv5yYlSwMP4Brb58NQ
CODEN IGRSD2
CitedBy_id crossref_primary_10_1109_TGRS_2024_3377999
crossref_primary_10_1109_LGRS_2024_3401728
crossref_primary_10_1109_JSTARS_2025_3574229
crossref_primary_10_1109_TGRS_2025_3541871
crossref_primary_10_1109_JSTARS_2024_3438620
crossref_primary_10_1109_JSTARS_2024_3439516
crossref_primary_10_1109_JSTARS_2024_3470316
crossref_primary_10_1109_TGRS_2024_3363742
crossref_primary_10_1109_TGRS_2025_3578515
crossref_primary_10_1109_TGRS_2025_3526247
crossref_primary_10_1109_TGRS_2024_3453501
crossref_primary_10_1109_TGRS_2024_3388528
crossref_primary_10_1109_TGRS_2025_3529031
crossref_primary_10_1109_TGRS_2025_3559915
crossref_primary_10_1109_JSTARS_2025_3594044
crossref_primary_10_1109_JSTARS_2025_3566159
crossref_primary_10_1109_TGRS_2024_3421651
crossref_primary_10_1117_1_JRS_19_014502
crossref_primary_10_1109_TGRS_2024_3404922
crossref_primary_10_1109_TIP_2024_3422881
crossref_primary_10_1080_01431161_2023_2274820
crossref_primary_10_1080_17538947_2024_2403619
crossref_primary_10_1109_JSTARS_2024_3424831
crossref_primary_10_1109_JSTARS_2025_3525634
crossref_primary_10_1190_geo2024_0245_1
crossref_primary_10_1109_TGRS_2024_3424295
crossref_primary_10_1109_JSTARS_2025_3571814
crossref_primary_10_1109_TGRS_2023_3318788
crossref_primary_10_3390_rs16132289
crossref_primary_10_1007_s11760_024_03255_5
crossref_primary_10_1109_JSTARS_2024_3388464
crossref_primary_10_1109_TGRS_2024_3385318
crossref_primary_10_1109_ACCESS_2024_3522286
crossref_primary_10_1109_JSTARS_2024_3417211
crossref_primary_10_1109_TGRS_2025_3543821
crossref_primary_10_1109_TGRS_2024_3410977
crossref_primary_10_1109_TGRS_2024_3516501
crossref_primary_10_1109_TGRS_2024_3427370
crossref_primary_10_1038_s41598_024_63575_x
crossref_primary_10_1109_JSTARS_2024_3378301
crossref_primary_10_1109_TGRS_2024_3482688
crossref_primary_10_1109_JSTARS_2025_3583442
crossref_primary_10_1109_TMM_2025_3543026
crossref_primary_10_1007_s00530_025_01674_z
crossref_primary_10_1109_TGRS_2024_3385747
crossref_primary_10_1109_TGRS_2025_3568475
crossref_primary_10_1109_JSTARS_2024_3485239
crossref_primary_10_1109_TGRS_2024_3521483
crossref_primary_10_1109_TGRS_2025_3589235
crossref_primary_10_1109_TGRS_2024_3492008
Cites_doi 10.1007/978-3-540-77058-9_42
10.1016/j.ins.2022.04.006
10.1109/TIP.2018.2878958
10.1007/978-3-030-01228-1_26
10.1109/CVPR.2017.660
10.1016/j.ijdrr.2018.11.022
10.1007/s00521-022-07737-w
10.1109/LGRS.2018.2795531
10.3390/rs12071130
10.1080/01431160512331316469
10.1007/978-3-030-58452-8_13
10.1109/TGRS.2022.3144894
10.1109/TGRS.2020.3015157
10.1007/s12665-011-1112-y
10.3390/rs11161922
10.1109/TGRS.2021.3103517
10.1109/TGRS.2022.3144165
10.1109/ICCV48922.2021.00061
10.1109/TGRS.2021.3093977
10.3390/s18103232
10.1016/j.isprsjprs.2021.01.020
10.3390/en14102960
10.1109/ICCV48922.2021.01204
10.1109/CVPRW50498.2020.00107
10.1109/TGRS.2020.3016820
10.1109/CVPR52688.2022.00398
10.1016/j.isprsjprs.2020.01.013
10.1109/ICCV48922.2021.00717
10.3390/rs13040808
10.1109/LGRS.2020.2988294
10.1109/CVPR.2016.90
10.3390/rs13010071
10.1109/TPAMI.2020.2983686
10.3390/rs12040701
10.1109/ICCV48922.2021.00986
10.1016/j.isprsjprs.2019.04.015
10.1109/CVPR46437.2021.00681
10.1109/CVPR.2015.7298965
10.1109/JSTARS.2021.3119654
10.5194/isprs-archives-XLII-2-W16-273-2019
10.1007/978-3-030-01240-3_17
10.3390/rs13183585
10.1007/s12145-018-00376-7
10.1109/TGRS.2021.3124913
10.1109/ICCV.2017.324
10.1016/j.eswa.2023.119508
10.1109/LGRS.2022.3143368
10.1109/TGRS.2020.2994150
10.1109/CVPRW.2016.90
10.1016/j.eswa.2020.114532
10.1016/j.eswa.2023.119858
10.1016/j.isprsjprs.2022.06.008
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7UA
8FD
C1K
F1W
FR3
H8D
H96
KR7
L.G
L7M
DOI 10.1109/TGRS.2023.3302024
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Water Resources Abstracts
Technology Research Database
Environmental Sciences and Pollution Management
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
Technology Research Database
ASFA: Aquatic Sciences and Fisheries Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Water Resources Abstracts
Environmental Sciences and Pollution Management
DatabaseTitleList
Aerospace Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1558-0644
EndPage 15
ExternalDocumentID 10_1109_TGRS_2023_3302024
10209224
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62171381
  funderid: 10.13039/501100001809
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AFRAH
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IBMZZ
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
RXW
TAE
TN5
VH1
Y6R
AAYXX
CITATION
7UA
8FD
C1K
F1W
FR3
H8D
H96
KR7
L.G
L7M
ID FETCH-LOGICAL-c294t-b09a91ccd2f0bfbdc349cd93ec01adf8c49978b0e5be5c611cecf3379561c1d53
IEDL.DBID RIE
ISICitedReferencesCount 86
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001050018600040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0196-2892
IngestDate Mon Jun 30 10:08:26 EDT 2025
Tue Nov 18 21:19:29 EST 2025
Sat Nov 29 03:32:25 EST 2025
Wed Aug 27 02:14:49 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c294t-b09a91ccd2f0bfbdc349cd93ec01adf8c49978b0e5be5c611cecf3379561c1d53
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8018-596X
0000-0001-5007-8533
0009-0009-5689-8271
0000-0003-4533-3880
PQID 2851333892
PQPubID 85465
PageCount 15
ParticipantIDs crossref_primary_10_1109_TGRS_2023_3302024
proquest_journals_2851333892
crossref_citationtrail_10_1109_TGRS_2023_3302024
ieee_primary_10209224
PublicationCentury 2000
PublicationDate 20230000
2023-00-00
20230101
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – year: 2023
  text: 20230000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev TGRS
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref57
ref12
ref56
ref15
ref59
ref14
ref58
ref53
dosovitskiy (ref34) 2021
ref52
ref11
ref55
ref10
ref54
ref17
ronneberger (ref19) 2015
ref16
ref18
ref50
chen (ref51) 2018
ref46
ref45
ref48
ref42
ref44
ref43
cao (ref68) 2021
ref49
wang (ref41) 2021
ref8
ref7
chu (ref37) 2021; 34
bao (ref47) 2021
ref9
ref4
vaswani (ref33) 2017
ref3
yu (ref69) 2015
ref6
ref36
ref31
ref30
ref32
ref2
ref1
ref39
ref38
zhou (ref20) 2018
xie (ref60) 2021
ref24
ref23
ramesh (ref65) 2021
ref26
ref25
devlin (ref64) 2018
ref63
ref22
ref66
ref21
ref28
ref27
ref29
(ref40) 2018
touvron (ref35) 2021; 139
ref62
ref61
yu (ref67) 2018
van westen (ref5) 2000; 33
References_xml – start-page: 3
  year: 2018
  ident: ref20
  article-title: UNet++: A nested U-Net architecture for medical image segmentation
  publication-title: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support
– ident: ref16
  doi: 10.1007/978-3-540-77058-9_42
– ident: ref30
  doi: 10.1016/j.ins.2022.04.006
– ident: ref29
  doi: 10.1109/TIP.2018.2878958
– start-page: 1
  year: 2021
  ident: ref34
  article-title: An image is worth 16×16 words: Transformers for image recognition at scale
  publication-title: Proc Int Conf Learn Represent
– year: 2021
  ident: ref47
  article-title: BEiT: BERT pre-training of image transformers
  publication-title: arXiv 2106 08254
– ident: ref50
  doi: 10.1007/978-3-030-01228-1_26
– ident: ref48
  doi: 10.1109/CVPR.2017.660
– ident: ref4
  doi: 10.1016/j.ijdrr.2018.11.022
– ident: ref57
  doi: 10.1007/s00521-022-07737-w
– ident: ref26
  doi: 10.1109/LGRS.2018.2795531
– volume: 34
  start-page: 9355
  year: 2021
  ident: ref37
  article-title: Twins: Revisiting the design of spatial attention in vision transformers
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref7
  doi: 10.3390/rs12071130
– ident: ref1
  doi: 10.1080/01431160512331316469
– ident: ref61
  doi: 10.1007/978-3-030-58452-8_13
– ident: ref43
  doi: 10.1109/TGRS.2022.3144894
– ident: ref23
  doi: 10.1109/TGRS.2020.3015157
– ident: ref9
  doi: 10.1007/s12665-011-1112-y
– ident: ref54
  doi: 10.3390/rs11161922
– ident: ref17
  doi: 10.1109/TGRS.2021.3103517
– ident: ref42
  doi: 10.1109/TGRS.2022.3144165
– ident: ref38
  doi: 10.1109/ICCV48922.2021.00061
– ident: ref15
  doi: 10.1109/TGRS.2021.3093977
– start-page: 801
  year: 2018
  ident: ref51
  article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation
  publication-title: Proc Eur Conf Comput Vis (ECCV)
– year: 2021
  ident: ref68
  article-title: Swin-UNet: UNet-like pure transformer for medical image segmentation
  publication-title: arXiv 2105 05537
– ident: ref10
  doi: 10.3390/s18103232
– ident: ref14
  doi: 10.1016/j.isprsjprs.2021.01.020
– ident: ref8
  doi: 10.3390/en14102960
– ident: ref36
  doi: 10.1109/ICCV48922.2021.01204
– ident: ref3
  doi: 10.1109/CVPRW50498.2020.00107
– volume: 33
  start-page: 1609
  year: 2000
  ident: ref5
  article-title: Remote sensing for natural disaster management
  publication-title: Int Arch Photogramm Remote Sens
– ident: ref27
  doi: 10.1109/TGRS.2020.3016820
– ident: ref62
  doi: 10.1109/CVPR52688.2022.00398
– year: 2018
  ident: ref40
  publication-title: 2d semantic labeling dataset
– start-page: 8821
  year: 2021
  ident: ref65
  article-title: Zero-shot text-to-image generation
  publication-title: Proc Int Conf Mach Learn
– ident: ref13
  doi: 10.1016/j.isprsjprs.2020.01.013
– start-page: 12077
  year: 2021
  ident: ref60
  article-title: SegFormer: Simple and efficient design for semantic segmentation with transformers
  publication-title: Proc NIPS
– ident: ref59
  doi: 10.1109/ICCV48922.2021.00717
– ident: ref11
  doi: 10.3390/rs13040808
– ident: ref22
  doi: 10.1109/LGRS.2020.2988294
– ident: ref52
  doi: 10.1109/CVPR.2016.90
– ident: ref25
  doi: 10.3390/rs13010071
– ident: ref21
  doi: 10.1109/TPAMI.2020.2983686
– ident: ref56
  doi: 10.3390/rs12040701
– ident: ref39
  doi: 10.1109/ICCV48922.2021.00986
– start-page: 1
  year: 2018
  ident: ref64
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
  publication-title: Proc North Amer Chapter Assoc Comput Linguistics
– ident: ref12
  doi: 10.1016/j.isprsjprs.2019.04.015
– ident: ref58
  doi: 10.1109/CVPR46437.2021.00681
– start-page: 1
  year: 2017
  ident: ref33
  article-title: Attention is all you need
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2021
  ident: ref41
  article-title: LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation
  publication-title: arXiv 2110 08733
– year: 2015
  ident: ref69
  article-title: Multi-scale context aggregation by dilated convolutions
  publication-title: arXiv 1511 07122
– ident: ref18
  doi: 10.1109/CVPR.2015.7298965
– ident: ref46
  doi: 10.1109/JSTARS.2021.3119654
– ident: ref6
  doi: 10.5194/isprs-archives-XLII-2-W16-273-2019
– ident: ref49
  doi: 10.1007/978-3-030-01240-3_17
– start-page: 234
  year: 2015
  ident: ref19
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Proc Int Conf Med Image Comput Comput -Assist Intervent
– ident: ref45
  doi: 10.3390/rs13183585
– ident: ref55
  doi: 10.1007/s12145-018-00376-7
– ident: ref28
  doi: 10.1109/TGRS.2021.3124913
– ident: ref66
  doi: 10.1109/ICCV.2017.324
– ident: ref31
  doi: 10.1016/j.eswa.2023.119508
– ident: ref44
  doi: 10.1109/LGRS.2022.3143368
– ident: ref24
  doi: 10.1109/TGRS.2020.2994150
– ident: ref2
  doi: 10.1109/CVPRW.2016.90
– start-page: 325
  year: 2018
  ident: ref67
  article-title: BiSeNet: Bilateral segmentation network for real-time semantic segmentation
  publication-title: Proc Eur Conf Comput Vis (ECCV)
– volume: 139
  start-page: 10347
  year: 2021
  ident: ref35
  article-title: Training data-efficient image transformers & distillation through attention
  publication-title: Proc Int Conf Mach Learn
– ident: ref53
  doi: 10.1016/j.eswa.2020.114532
– ident: ref32
  doi: 10.1016/j.eswa.2023.119858
– ident: ref63
  doi: 10.1016/j.isprsjprs.2022.06.008
SSID ssj0014517
Score 2.641288
Snippet Transformer has been widely applied in image processing tasks as a substitute for convolutional neural networks (CNNs) for feature extraction due to its...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Ablation
Aggregation
Artificial neural networks
Coders
Context
Current transformers
Decoding
Encoder–decoder structure
Feature extraction
global-local transformer
Image acquisition
Image processing
Image segmentation
Information processing
Modelling
Modules
Neural networks
Remote sensing
remote sensing (RS)
Representations
Semantic segmentation
Semantics
Task analysis
Visualization
Title Rethinking Transformers for Semantic Segmentation of Remote Sensing Images
URI https://ieeexplore.ieee.org/document/10209224
https://www.proquest.com/docview/2851333892
Volume 61
WOSCitedRecordID wos001050018600040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1558-0644
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014517
  issn: 0196-2892
  databaseCode: RIE
  dateStart: 19800101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT9swED-NakjsAUYBrdBNedgTUoqTOHX8OE3AtodqKkXiLXLOF6hEU9QP_n7OjotAaJN4shXZVnQ_f9ydffcD-C4xtUbUVWyVplhmRsUmsS7hpdXWqJqnAXqyCTUaFTc3-m8IVvexMETkH5_RwFX9Xb6d49q5yniFp0LzmbMFW0qpNljr-cpA5kmIjR7GbEWk4QozEfpscjm-Gjie8AFb71zKV4eQZ1V5sxX78-Vi751_9hl2gyIZ_WiR34cP1HTh04v0gl3Y9s87cXkAf8a0umtZEqLJRlVlxS_iMrqiGYt3ily5nYVQpCaa19GYGEfiz41zKES_Z7z3LA_h-uJ88vNXHFgUYky1XMWV0EYniDatRVVXFjOp0eqMUCTG1gWyzaOKSlBeUY7DJEHCOsuUi3hFhi07gk4zb-gLRHlqtBWChrkhiUYYVvdkgVmVoyS2K3sgNmItMaQYd0wX96U3NYQuHRKlQ6IMSPTg9LnLQ5tf43-ND53oXzRspd6D_ga8MizBZZkWjrqG9bH0-B_dTmDHjd46VPrQWS3W9BU-4uNqulx887PrCYWGzN4
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB7yaEh7yLt02zx86CngjSzLa-tYQt7JEjYbyM3Io3Ea6HpDdtPf35GsDSklhZwkjITMfHrMjDTzAXxXKK0RdRXbXFOsUpPHJrEu4aXV1uQ1TwP0ZBN5v1_c3enrEKzuY2GIyD8-o66r-rt8O8Zn5yrjFS6F5jNnHhYzpWTShmu9XBqoLAnR0b2Y7QgZLjEToQ-GJ4ObrmMK77L9zqX66xjyvCr_bMb-hDlefee_rcFKUCWjHy326zBHzQZ8epVgcAOW_ANPnGzC-YCmP1uehGg4U1ZZ9Yu4jG5oxAJ-QK7cj0IwUhON62hAjCTx58a5FKKzEe8-ky24PT4aHp7GgUchRqnVNK6ENjpBtLIWVV1ZTJVGq1NCkRhbF8hWT15UgrKKMuwlCRLWaZq7mFdk4NLPsNCMG_oCUSaNtkJQLzOk0AjDCp8qMK0yVMSWZQfETKwlhiTjjuviV-mNDaFLh0TpkCgDEh3Yf-ny2GbY-F_jLSf6Vw1bqXdgewZeGRbhpJSFI69hjUx-faPbHiyfDq8uy8uz_sU3-OhGat0r27AwfXqmHfiAv6cPk6ddP9P-AFh10CU
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=Rethinking+Transformers+for+Semantic+Segmentation+of+Remote+Sensing+Images&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Liu%2C+Yuheng&rft.au=Zhang%2C+Yifan&rft.au=Wang%2C+Ye&rft.au=Mei%2C+Shaohui&rft.date=2023&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=61&rft.spage=1&rft.epage=15&rft_id=info:doi/10.1109%2FTGRS.2023.3302024&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2023_3302024
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon