GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification

Convolutional neural networks and transformers have been extensively utilized in hyperspectral image classification due to their exceptional feature learning capabilities. However, many existing patch-based classification methods often neglect the fusion of multiscale and multiangle features and can...

Full description

Saved in:
Bibliographic Details
Main Authors: Junding Sun, Haoxiang Dong, Yanlong Gao, Xiaosheng Wu, Jianlong Wang, Yudong Zhang
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/11117185/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228533630500864
author Junding Sun
Haoxiang Dong
Yanlong Gao
Xiaosheng Wu
Jianlong Wang
Yudong Zhang
author_facet Junding Sun
Haoxiang Dong
Yanlong Gao
Xiaosheng Wu
Jianlong Wang
Yudong Zhang
author_sort Junding Sun
collection DOAJ
description Convolutional neural networks and transformers have been extensively utilized in hyperspectral image classification due to their exceptional feature learning capabilities. However, many existing patch-based classification methods often neglect the fusion of multiscale and multiangle features and cannot fully capture the relationships between the central pixel and its neighboring pixels, which is likely to compromise the classification performance. To address these challenges, this article proposes a grouped multiscale multiangle feature fusion network with center attention (GM2FFNet). The proposed network unfolds in three key stages. First, a grouped multiscale extraction module captures and fuses spectral features at different scales using various kernels. Second, a grouped multiangle convolution module extracts features from multiple directions, with an adaptive fusion module further integrating this information. Finally, a spatial-spectral attention transformer module captures the correlations between the central pixel and its surrounding pixels. Experimental results on the Indian Pines, Pavia University, and Hi-LongKou datasets show that GM2FFNet achieves overall accuracies of 98.17%, 98.45%, and 99.03%, respectively, using only 7%, 0.7%, and 0.2% of the labeled samples, with a reduced number of parameters. Notably, the model significantly outperforms existing methods in several challenging categories across all three datasets. These results highlight both the effectiveness and robustness of the proposed network.
format Article
id doaj-art-aff87b870f964fab9aeda8e8e487fda3
institution Kabale University
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-aff87b870f964fab9aeda8e8e487fda32025-08-22T23:08:05ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118203752038910.1109/JSTARS.2025.359637811117185GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image ClassificationJunding Sun0https://orcid.org/0000-0001-7349-0248Haoxiang Dong1Yanlong Gao2https://orcid.org/0000-0002-3696-6398Xiaosheng Wu3https://orcid.org/0000-0003-1688-9564Jianlong Wang4https://orcid.org/0000-0001-8117-0631Yudong Zhang5https://orcid.org/0000-0002-4870-1493School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaSchool of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K.Convolutional neural networks and transformers have been extensively utilized in hyperspectral image classification due to their exceptional feature learning capabilities. However, many existing patch-based classification methods often neglect the fusion of multiscale and multiangle features and cannot fully capture the relationships between the central pixel and its neighboring pixels, which is likely to compromise the classification performance. To address these challenges, this article proposes a grouped multiscale multiangle feature fusion network with center attention (GM2FFNet). The proposed network unfolds in three key stages. First, a grouped multiscale extraction module captures and fuses spectral features at different scales using various kernels. Second, a grouped multiangle convolution module extracts features from multiple directions, with an adaptive fusion module further integrating this information. Finally, a spatial-spectral attention transformer module captures the correlations between the central pixel and its surrounding pixels. Experimental results on the Indian Pines, Pavia University, and Hi-LongKou datasets show that GM2FFNet achieves overall accuracies of 98.17%, 98.45%, and 99.03%, respectively, using only 7%, 0.7%, and 0.2% of the labeled samples, with a reduced number of parameters. Notably, the model significantly outperforms existing methods in several challenging categories across all three datasets. These results highlight both the effectiveness and robustness of the proposed network.https://ieeexplore.ieee.org/document/11117185/Hyperspectral image (HSI) classificationfeature fusioncentral pixelconvolutional neural network (CNN)transformer
spellingShingle Junding Sun
Haoxiang Dong
Yanlong Gao
Xiaosheng Wu
Jianlong Wang
Yudong Zhang
GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Hyperspectral image (HSI) classification
feature fusion
central pixel
convolutional neural network (CNN)
transformer
title GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
title_full GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
title_fullStr GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
title_full_unstemmed GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
title_short GM2FFNet: Grouped Multiscale Multiangle Feature Fusion Network With Center Attention for Hyperspectral Image Classification
title_sort gm2ffnet grouped multiscale multiangle feature fusion network with center attention for hyperspectral image classification
topic Hyperspectral image (HSI) classification
feature fusion
central pixel
convolutional neural network (CNN)
transformer
url https://ieeexplore.ieee.org/document/11117185/
work_keys_str_mv AT jundingsun gm2ffnetgroupedmultiscalemultianglefeaturefusionnetworkwithcenterattentionforhyperspectralimageclassification
AT haoxiangdong gm2ffnetgroupedmultiscalemultianglefeaturefusionnetworkwithcenterattentionforhyperspectralimageclassification
AT yanlonggao gm2ffnetgroupedmultiscalemultianglefeaturefusionnetworkwithcenterattentionforhyperspectralimageclassification
AT xiaoshengwu gm2ffnetgroupedmultiscalemultianglefeaturefusionnetworkwithcenterattentionforhyperspectralimageclassification
AT jianlongwang gm2ffnetgroupedmultiscalemultianglefeaturefusionnetworkwithcenterattentionforhyperspectralimageclassification
AT yudongzhang gm2ffnetgroupedmultiscalemultianglefeaturefusionnetworkwithcenterattentionforhyperspectralimageclassification