Multi-Spectral Band Selection and Spatial Explanations Using XAI Algorithms in Remote Sensing Applications
This work proposes an interpretable Deep Learning framework utilizing Vision Transformers (ViT) for the classification of remote sensing images into land use and land cover (LULC) classes. It uses the Shapley Additive Explanations (SHAP) values to achieve two-stage explanations: 1) bandwise feature...
Saved in:
Published in | IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium pp. 6093 - 6396 |
---|---|
Main Authors | , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
16.07.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | This work proposes an interpretable Deep Learning framework utilizing Vision Transformers (ViT) for the classification of remote sensing images into land use and land cover (LULC) classes. It uses the Shapley Additive Explanations (SHAP) values to achieve two-stage explanations: 1) bandwise feature importance per class, showing which band assists the prediction of each class and 2) spatial-wise feature understanding, explaining which embedded patches per band affected the network's performance. Experimental results on the EuroSAT dataset demonstrate the ViT's accurate classification with an overall accuracy 96.86 %, offering improved results when compared to popular CNN models. Heatmaps in each one of the dataset's existing classes highlight the effectiveness of the proposed framework in the band explanation and the feature importance. |
---|---|
AbstractList | This work proposes an interpretable Deep Learning framework utilizing Vision Transformers (ViT) for the classification of remote sensing images into land use and land cover (LULC) classes. It uses the Shapley Additive Explanations (SHAP) values to achieve two-stage explanations: 1) bandwise feature importance per class, showing which band assists the prediction of each class and 2) spatial-wise feature understanding, explaining which embedded patches per band affected the network's performance. Experimental results on the EuroSAT dataset demonstrate the ViT's accurate classification with an overall accuracy 96.86 %, offering improved results when compared to popular CNN models. Heatmaps in each one of the dataset's existing classes highlight the effectiveness of the proposed framework in the band explanation and the feature importance. |
Author | Doulamis, Anastasios Kaselimi, Maria Temenos, Anastasios Temenos, Nikos Doulamis, Nikolaos |
Author_xml | – sequence: 1 givenname: Anastasios surname: Temenos fullname: Temenos, Anastasios organization: National Technical University of Athens – sequence: 2 givenname: Nikos surname: Temenos fullname: Temenos, Nikos organization: National Technical University of Athens – sequence: 3 givenname: Maria surname: Kaselimi fullname: Kaselimi, Maria organization: National Technical University of Athens – sequence: 4 givenname: Anastasios surname: Doulamis fullname: Doulamis, Anastasios organization: National Technical University of Athens – sequence: 5 givenname: Nikolaos surname: Doulamis fullname: Doulamis, Nikolaos organization: National Technical University of Athens |
BookMark | eNo1UEFOwzAQNAgk2tIfcDAPSFivY8c5hqqUSkVIDZW4VU7tFFeuEyVBgt8TWpjL7szuzGHG5CrUwRJyzyBmDLKH5SJfF4VABipGQB4zQIVCigsyzdJMcQEcgUF6SUbIBI9SAH5Dxl13GBaFACNyePn0vYuKxu76Vnv6qIOhhfUDdXWgJ9bo3g2n-VfjddC_ekc3nQt7-p4vae73dev6j2NHXaBre6x7OySE00PeNN7tzp5bcl1p39np35yQzdP8bfYcrV4Xy1m-ihxC0kdWAhosOauQs9KUxphMlGgrmZU2VUwkOjEgq2QnhVSgTFlpbSzKASmvgE_I3TnXWWu3TeuOuv3e_nfDfwDtA1zW |
ContentType | Conference Proceeding |
DBID | 6IE 6IH CBEJK RIE RIO |
DOI | 10.1109/IGARSS52108.2023.10282565 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Geology |
EISBN | 9798350320107 |
EISSN | 2153-7003 |
EndPage | 6396 |
ExternalDocumentID | 10282565 |
Genre | orig-research |
GroupedDBID | 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IPLJI OCL RIE RIL RIO RNS |
ID | FETCH-LOGICAL-i204t-e602d2b31f231bdbddd95b2ef69be78154a4d06f4c656808dbfaade2666673f03 |
IEDL.DBID | RIE |
IngestDate | Wed Jun 26 19:24:09 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i204t-e602d2b31f231bdbddd95b2ef69be78154a4d06f4c656808dbfaade2666673f03 |
PageCount | 304 |
ParticipantIDs | ieee_primary_10282565 |
PublicationCentury | 2000 |
PublicationDate | 2023-July-16 |
PublicationDateYYYYMMDD | 2023-07-16 |
PublicationDate_xml | – month: 07 year: 2023 text: 2023-July-16 day: 16 |
PublicationDecade | 2020 |
PublicationTitle | IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium |
PublicationTitleAbbrev | IGARSS |
PublicationYear | 2023 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0038200 |
Score | 1.8925385 |
Snippet | This work proposes an interpretable Deep Learning framework utilizing Vision Transformers (ViT) for the classification of remote sensing images into land use... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 6093 |
SubjectTerms | Correlation Deep learning EuroSAT Heating systems Land Cover Land Use Remote Sensing Rivers Satellite images Sensors Sentinel-2 SHAP Transformers ViT XAI |
Title | Multi-Spectral Band Selection and Spatial Explanations Using XAI Algorithms in Remote Sensing Applications |
URI | https://ieeexplore.ieee.org/document/10282565 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1bS8MwFA5uoPjkbeKdCL62S9Mmax6ruE3BIZuDvY2kOdV56WTrHvTXm6SrNxB8670lB_Kdnnzf-RA6kwGwTIRgZj8VexFNI08FWnmEkzBkIpPCUf5verw7jK5HbLQUqzstDAA48hn4dtOt5etpurClsmbglJac1VAtJrQUa1XTbmigjKyh02UTzeZVJ-kPBgaciCVw0dCvbv5ho-JQpL2BetX7S_LIk78olJ--_2rN-O8P3ESNL8Eevv2Eoi20Avk2Wu041963HfToZLae9Zq3hQ18LnONB84Bx4QFuz3LrDanLCdPlhXCOXZ8AjxKrnDyfD-dTYqHlzme5LgPJsBgnpC7C5Jvi-ANNGxf3l10vaXJgjehJCo84IRqqsIgM5me0kprLZiikHGhoBWbDEtGmvAsSk3mF5NYq0xKDQbXrWFoRsJdVM-nOewhLJUQlKWBUOY3p0WoYjrgJv3SDJhQrWwfNeyQjV_LPhrjarQO_jh-iNZt5GwlNeBHqF7MFnBsUoBCnbjQfwAe4LD_ |
link.rule.ids | 310,311,786,790,795,796,802,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3JTsMwFLSgiOXEVsSOkbimdRY78TEgukBboS5Sb5Ud21CWFLXpAb4e22nYJCRuSZxEll_keXme8QBwwVyJFfWlnv145AReEjjcFdxBBPk-popRS_lvd0hjENwM8XAhVrdaGCmlJZ_Jijm0a_liksxNqazqWqUlwctgRQM9CnO5VjHx-hrM0Bo4X2yjWW3W426vp-EJGQqX51eKx38YqVgcqW2CTtGDnD7yVJlnvJK8_9qc8d9d3ALlL8kevPsEo22wJNMdsFq3vr1vu-DRCm0d4zZvShvwkqUC9qwHjg4MtGeGW62bDCuP5TXCGbSMAjiMmzB-vp9Mx9nDywyOU9iVOsRSvyG1N8TflsHLYFC77l81nIXNgjP2UJA5kiBPeNx3lc71uOBCCIq5JxWhXIaRzrFYIBBRQaJzvwhFgivGhNTIbixDFfL3QCmdpHIfQMYp9XDiUq5_dELkcSxcohMwgSWmPFQHoGyGbPSa76QxKkbr8I_rZ2C90W-3Rq1m5_YIbJgomrqqS45BKZvO5YlOCDJ-aj-DD58ctFM |
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%3Abook&rft.genre=proceeding&rft.title=IGARSS+2023+-+2023+IEEE+International+Geoscience+and+Remote+Sensing+Symposium&rft.atitle=Multi-Spectral+Band+Selection+and+Spatial+Explanations+Using+XAI+Algorithms+in+Remote+Sensing+Applications&rft.au=Temenos%2C+Anastasios&rft.au=Temenos%2C+Nikos&rft.au=Kaselimi%2C+Maria&rft.au=Doulamis%2C+Anastasios&rft.date=2023-07-16&rft.pub=IEEE&rft.eissn=2153-7003&rft.spage=6093&rft.epage=6396&rft_id=info:doi/10.1109%2FIGARSS52108.2023.10282565&rft.externalDocID=10282565 |