Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification

Graph Neural Networks (GNNs) have emerged as a promising solution for few-shot hyperspectral image (HSI) classification. However, existing GNN-based approaches face critical limitations in three key aspects: 1) suboptimal graph topology construction due to fixed or heuristic-based edge definitions,...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaoxia Xue, Zhiwei Liu, Zhaohui Xue, Tingqiang Song
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11003994/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255676520005632
author Zhaoxia Xue
Zhiwei Liu
Zhaohui Xue
Tingqiang Song
author_facet Zhaoxia Xue
Zhiwei Liu
Zhaohui Xue
Tingqiang Song
author_sort Zhaoxia Xue
collection DOAJ
description Graph Neural Networks (GNNs) have emerged as a promising solution for few-shot hyperspectral image (HSI) classification. However, existing GNN-based approaches face critical limitations in three key aspects: 1) suboptimal graph topology construction due to fixed or heuristic-based edge definitions, 2) inefficient propagation of discriminative node features across heterogeneous regions, and 3) inadequate fusion of spatially correlated and spectrally discriminative patterns. To overcome these challenges, we propose a Spatial-Spectral Contrastive Graph Neural Network (SSCGNN), which introduces three novel components. First, we propose a directed graph reconstruction module that transforms conventional undirected graphs into diversity-aware topology through multi-head self-attention mechanisms. Second, we design a collaborative learning framework where the spatial graph network and spectral graph network mutually enhance feature extraction. Finally, we construct a graph contrastive learning module that augments edge representation learning under limited supervision. By constructing positive/negative edge pairs through spectral-spatial similarity metrics, it regularizes the graph structure to emphasize class-discriminative connections and suppress noisy inter-node relationships. Extensive experiments on four benchmark HSI datasets—University of Pavia (PU), Salinas Valley (SA), WHU-Hi-HanChuan (WHU-HH), and WHU-Hi-LongKou (WHU-HL)—demonstrate SSCGNN’s superiority over state-of-the-art few-shot learning methods. With only 5 labeled samples per class, our model achieves overall accuracy (OA) values of: 93.36% (PU, +6.22% vs. baseline GCN), 98.37% (SA, +4.91% vs. spectral-spatial CNN), 84.68% (WHU-HH, +8.03% vs. meta-learning approaches), 95.87% (WHU-HL, +7.15% vs. graph attention networks).
format Article
id doaj-art-4592c327e9534b9c81bcac623b834ed1
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4592c327e9534b9c81bcac623b834ed12025-08-20T01:56:48ZengIEEEIEEE Access2169-35362025-01-0113882788829010.1109/ACCESS.2025.356987411003994Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image ClassificationZhaoxia Xue0Zhiwei Liu1Zhaohui Xue2https://orcid.org/0000-0001-6253-2967Tingqiang Song3School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, ChinaiFLYTEK Company Ltd., Hefei, ChinaCollege of Geography and Remote Sensing, Hohai University, Nanjing, ChinaSchool of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, ChinaGraph Neural Networks (GNNs) have emerged as a promising solution for few-shot hyperspectral image (HSI) classification. However, existing GNN-based approaches face critical limitations in three key aspects: 1) suboptimal graph topology construction due to fixed or heuristic-based edge definitions, 2) inefficient propagation of discriminative node features across heterogeneous regions, and 3) inadequate fusion of spatially correlated and spectrally discriminative patterns. To overcome these challenges, we propose a Spatial-Spectral Contrastive Graph Neural Network (SSCGNN), which introduces three novel components. First, we propose a directed graph reconstruction module that transforms conventional undirected graphs into diversity-aware topology through multi-head self-attention mechanisms. Second, we design a collaborative learning framework where the spatial graph network and spectral graph network mutually enhance feature extraction. Finally, we construct a graph contrastive learning module that augments edge representation learning under limited supervision. By constructing positive/negative edge pairs through spectral-spatial similarity metrics, it regularizes the graph structure to emphasize class-discriminative connections and suppress noisy inter-node relationships. Extensive experiments on four benchmark HSI datasets—University of Pavia (PU), Salinas Valley (SA), WHU-Hi-HanChuan (WHU-HH), and WHU-Hi-LongKou (WHU-HL)—demonstrate SSCGNN’s superiority over state-of-the-art few-shot learning methods. With only 5 labeled samples per class, our model achieves overall accuracy (OA) values of: 93.36% (PU, +6.22% vs. baseline GCN), 98.37% (SA, +4.91% vs. spectral-spatial CNN), 84.68% (WHU-HH, +8.03% vs. meta-learning approaches), 95.87% (WHU-HL, +7.15% vs. graph attention networks).https://ieeexplore.ieee.org/document/11003994/Hyperspectral image (HSI)classificationcontrastive learninggraph neural networks (GNNs)few-shot learning
spellingShingle Zhaoxia Xue
Zhiwei Liu
Zhaohui Xue
Tingqiang Song
Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification
IEEE Access
Hyperspectral image (HSI)
classification
contrastive learning
graph neural networks (GNNs)
few-shot learning
title Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification
title_full Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification
title_fullStr Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification
title_full_unstemmed Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification
title_short Spatial-Spectral Contrastive Graph Neural Network for Few-Shot Hyperspectral Image Classification
title_sort spatial spectral contrastive graph neural network for few shot hyperspectral image classification
topic Hyperspectral image (HSI)
classification
contrastive learning
graph neural networks (GNNs)
few-shot learning
url https://ieeexplore.ieee.org/document/11003994/
work_keys_str_mv AT zhaoxiaxue spatialspectralcontrastivegraphneuralnetworkforfewshothyperspectralimageclassification
AT zhiweiliu spatialspectralcontrastivegraphneuralnetworkforfewshothyperspectralimageclassification
AT zhaohuixue spatialspectralcontrastivegraphneuralnetworkforfewshothyperspectralimageclassification
AT tingqiangsong spatialspectralcontrastivegraphneuralnetworkforfewshothyperspectralimageclassification