PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)

This paper Introduces a novel method for Polarimetric Synthetic Aperture Radar (PolSAR) image classification using a Complex-Valued Multiscale Attention Vision Transformer (CV-MsAtViT). The model incorporates a complex-valued multiscale feature fusion mechanism, a complex-valued attention block, and...

Full description

Saved in:
Bibliographic Details
Main Author: Mohammed Q. Alkhatib
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225000597
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850252570022379520
author Mohammed Q. Alkhatib
author_facet Mohammed Q. Alkhatib
author_sort Mohammed Q. Alkhatib
collection DOAJ
description This paper Introduces a novel method for Polarimetric Synthetic Aperture Radar (PolSAR) image classification using a Complex-Valued Multiscale Attention Vision Transformer (CV-MsAtViT). The model incorporates a complex-valued multiscale feature fusion mechanism, a complex-valued attention block, and a Complex-Valued Vision Transformer (CV-ViT) to effectively capture spatial and polarimetric features from PolSAR data. The multiscale fusion block enhances feature extraction, while the attention mechanism prioritizes critical features, and the CV-ViT processes data in the complex domain, preserving both amplitude and phase information. Experimental results on benchmark PolSAR datasets, including Flevoland, San Francisco, and Oberpfaffenhofen, show that CV-MsAtViT achieves superior classification accuracy, with an overall accuracy (OA) of 98.35% on the Flevoland dataset, outperforming state-of-the-art models like PolSARFormer. The model also demonstrates efficient computational performance, minimizing the number of parameters while preserving high accuracy. These results confirm that CV-MsAtViT effectively enhances the classification of PolSAR images by leveraging complex-valued data processing, offering a promising direction for future advancements in remote sensing and complex-valued deep learning.The codes associated with this paper are publicly available at https://github.com/mqalkhatib/CV-MsAtViT.
format Article
id doaj-art-9c5deb3d95724568bf9a0ab5fecce0f6
institution OA Journals
issn 1569-8432
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-9c5deb3d95724568bf9a0ab5fecce0f62025-08-20T01:57:36ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-03-0113710441210.1016/j.jag.2025.104412PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)Mohammed Q. Alkhatib0College of Engineering and IT, University of Dubai, Dubai, 14143, United Arab EmiratesThis paper Introduces a novel method for Polarimetric Synthetic Aperture Radar (PolSAR) image classification using a Complex-Valued Multiscale Attention Vision Transformer (CV-MsAtViT). The model incorporates a complex-valued multiscale feature fusion mechanism, a complex-valued attention block, and a Complex-Valued Vision Transformer (CV-ViT) to effectively capture spatial and polarimetric features from PolSAR data. The multiscale fusion block enhances feature extraction, while the attention mechanism prioritizes critical features, and the CV-ViT processes data in the complex domain, preserving both amplitude and phase information. Experimental results on benchmark PolSAR datasets, including Flevoland, San Francisco, and Oberpfaffenhofen, show that CV-MsAtViT achieves superior classification accuracy, with an overall accuracy (OA) of 98.35% on the Flevoland dataset, outperforming state-of-the-art models like PolSARFormer. The model also demonstrates efficient computational performance, minimizing the number of parameters while preserving high accuracy. These results confirm that CV-MsAtViT effectively enhances the classification of PolSAR images by leveraging complex-valued data processing, offering a promising direction for future advancements in remote sensing and complex-valued deep learning.The codes associated with this paper are publicly available at https://github.com/mqalkhatib/CV-MsAtViT.http://www.sciencedirect.com/science/article/pii/S1569843225000597PolSAR image classificationComplex-valued (CV) networksFeature fusionCV coordinate attentionCV vision transformers (CV-viT)
spellingShingle Mohammed Q. Alkhatib
PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)
International Journal of Applied Earth Observations and Geoinformation
PolSAR image classification
Complex-valued (CV) networks
Feature fusion
CV coordinate attention
CV vision transformers (CV-viT)
title PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)
title_full PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)
title_fullStr PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)
title_full_unstemmed PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)
title_short PolSAR image classification using complex-valued multiscale attention vision transformer (CV-MsAtViT)
title_sort polsar image classification using complex valued multiscale attention vision transformer cv msatvit
topic PolSAR image classification
Complex-valued (CV) networks
Feature fusion
CV coordinate attention
CV vision transformers (CV-viT)
url http://www.sciencedirect.com/science/article/pii/S1569843225000597
work_keys_str_mv AT mohammedqalkhatib polsarimageclassificationusingcomplexvaluedmultiscaleattentionvisiontransformercvmsatvit