EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification

Hyperspectral image (HSI) classification, as a pivotal technology in remote sensing data processing, has garnered significant attention in recent years. Deep learning (DL) has been widely adopted for HSI classification due to its superior feature extraction capabilities. Nevertheless, the deployment...

Full description

Saved in:
Bibliographic Details
Main Authors: Hufeng Guo, Wenyi Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10989234/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850269632515014656
author Hufeng Guo
Wenyi Liu
author_facet Hufeng Guo
Wenyi Liu
author_sort Hufeng Guo
collection DOAJ
description Hyperspectral image (HSI) classification, as a pivotal technology in remote sensing data processing, has garnered significant attention in recent years. Deep learning (DL) has been widely adopted for HSI classification due to its superior feature extraction capabilities. Nevertheless, the deployment of most existing DL models on resource-constrained devices remains challenging because of their intricate architectures and high computational demands. To tackle this challenge, we propose a lightweight dual-branch convolutional transformer network with efficient attention-aware mechanism (EDB-Net), which aims to balance model complexity, classification accuracy, and inference speed. EDB-Net achieves this by conducting an in-depth analysis and modeling of spatial-spectral features through two independent pipelines: one based on convolutional neural networks and the other on Transformer, thereby leveraging the complementary strengths of both approaches. Specifically, we introduce a novel lightweight spatial-spectral Transformer that incorporates a lightweight multi-head efficient attention-aware mechanism. This design ingeniously mitigates the quadratic growth of computational complexity associated with the standard self-attention mechanism's softmax calculation via the agent tokens approach. In addition, by correlating the self-attention map with the query vector, our model accurately extracts useful information to generate an attention gate that highlights key elements of the spectral sequence. Furthermore, the gated recurrent unit is incorporated into the algorithm to enhance the learning and analytical capabilities for spectral sequence data. Experimental results demonstrate that EDB-Net maintains high classification accuracy while significantly reducing computational complexity, outperforming existing state-of-the-art methods.
format Article
id doaj-art-8de23a3bb00645e4a26c8f062ea26e9d
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-8de23a3bb00645e4a26c8f062ea26e9d2025-08-20T01:53:04ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118124851250010.1109/JSTARS.2025.356748510989234EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image ClassificationHufeng Guo0https://orcid.org/0009-0008-0685-6121Wenyi Liu1https://orcid.org/0000-0002-4098-0256State Key Laboratory of Dynamic Measurement Technology, School of Instrument and Electronics, North University of China, Taiyuan, ChinaState Key Laboratory of Dynamic Measurement Technology, School of Instrument and Electronics, North University of China, Taiyuan, ChinaHyperspectral image (HSI) classification, as a pivotal technology in remote sensing data processing, has garnered significant attention in recent years. Deep learning (DL) has been widely adopted for HSI classification due to its superior feature extraction capabilities. Nevertheless, the deployment of most existing DL models on resource-constrained devices remains challenging because of their intricate architectures and high computational demands. To tackle this challenge, we propose a lightweight dual-branch convolutional transformer network with efficient attention-aware mechanism (EDB-Net), which aims to balance model complexity, classification accuracy, and inference speed. EDB-Net achieves this by conducting an in-depth analysis and modeling of spatial-spectral features through two independent pipelines: one based on convolutional neural networks and the other on Transformer, thereby leveraging the complementary strengths of both approaches. Specifically, we introduce a novel lightweight spatial-spectral Transformer that incorporates a lightweight multi-head efficient attention-aware mechanism. This design ingeniously mitigates the quadratic growth of computational complexity associated with the standard self-attention mechanism's softmax calculation via the agent tokens approach. In addition, by correlating the self-attention map with the query vector, our model accurately extracts useful information to generate an attention gate that highlights key elements of the spectral sequence. Furthermore, the gated recurrent unit is incorporated into the algorithm to enhance the learning and analytical capabilities for spectral sequence data. Experimental results demonstrate that EDB-Net maintains high classification accuracy while significantly reducing computational complexity, outperforming existing state-of-the-art methods.https://ieeexplore.ieee.org/document/10989234/Convolutional neural networks (CNNS)hyperspectral image (HSI)self-attention mechanismtransformer
spellingShingle Hufeng Guo
Wenyi Liu
EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Convolutional neural networks (CNNS)
hyperspectral image (HSI)
self-attention mechanism
transformer
title EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification
title_full EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification
title_fullStr EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification
title_full_unstemmed EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification
title_short EDB-Net: Efficient Dual-Branch Convolutional Transformer Network for Hyperspectral Image Classification
title_sort edb net efficient dual branch convolutional transformer network for hyperspectral image classification
topic Convolutional neural networks (CNNS)
hyperspectral image (HSI)
self-attention mechanism
transformer
url https://ieeexplore.ieee.org/document/10989234/
work_keys_str_mv AT hufengguo edbnetefficientdualbranchconvolutionaltransformernetworkforhyperspectralimageclassification
AT wenyiliu edbnetefficientdualbranchconvolutionaltransformernetworkforhyperspectralimageclassification