| 0 | 0 | 4 |
| Downloads | Citas | Reads |
To address the issues of limited receptive fields in conventional graph convolutional networks(GCNs), over-smoothing caused by deep network stacking, and information redundancy in spatial-spectral interactions for hyperspectral image classification, an adaptive multi-hop graph convolution and Transformer fusion network was proposed. An adaptive multi-hop graph attention layer was designed to achieve the adaptive weighted fusion of 0-to K-hop neighborhood features via learnable attention vectors. Concurrently, an enhanced GCN-Transformer fusion interface was constructed by integrating a channel attention mechanism and a one-dimensional neighborhood convolution module, thereby effectively compressing the channel redundancy of the node embeddings and elevating the spectral discriminability. The results on the Indian Pines, Salinas, and Pavia University datasets demonstrate that the proposed method achieves classification accuracies of 96.05%, 96.92%, and 96.28%, outperforming the classic GTFN method by 2.05,0.11, and 1.14 percentage points, respectively. These results confirm that the synergistic effect of multihop spatial topology modeling and enhanced spectral sequence fusion can effectively overcome the “curse of dimensionality” in hyperspectral and significantly improve the delineation accuracy of irregular boundaries.The introduction of spatial graph modeling boosts the overall accuracy by 27.91 percentage points, with adaptive weighting achieving optimal performance at a hop count of K=3, indicating that the adaptive multihop graph attention mechanism can broaden the spatial perspectives with lower computational overhead and reduce over-smoothing risks by utilizing learned weight decay regularities. By incorporating a feature interface into the channel attention module, the model yields the best comprehensive performance, demonstrating that the enhanced interface effectively compresses information redundancy during the interaction phase,which strengthens the discriminative capability for highly similar spectral land covers.
[1]Hu Wei, Huang Yangyu, Wei Li, et al. Deep convolutional neural networks for hyperspectral image classification[J].Journal of Sensors, 2015(1):258619.
[2]Li Shutao,Song Weiwei,Fang Leyuan,et al.Deep learning for hyperspectral image classification:an overview[J].IEEE Transactions on Geoscience and Remote Sensing,2019,57(9):6690-6709.
[3]Hughes G.On the mean accuracy of statistical pattern recognizers[J]. IEEE Transactions on Information Theory,1968,14(1):55-63.
[4]Melgani F,Bruzzone L.Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.
[5]Amini S,Homayouni S,Safari A,et al.Objectbased classification of hyperspectral data using random forest algorithm[J]. Geo-spatial Information Science,2018,21(2):127-138.
[6]迟骋，李向阳，张志利，等．基于动态卷积的混合模型性能评估方法[J]．火箭军工程大学学报，2024,38(5):53-58,80.Chi Cheng,Li Xiangyang,Zhang Zhili,et al.Performance evaluation method of hybrid model based on dynamic convolution[J].Journal of Rocket Force University of Engineering, 2024, 38(5):53-58,80.
[7]李邦杰，武健，张大巧，等．基于卷积神经网络的景象匹配区适配性筛选方法[J]．火箭军工程大学学报，2024,38(3):45-50,59.Li Bangjie, Wu Jian, Zhang Daqiao, et al. A CNN-based scene matching adaptability screening method[J]. Journal of Rocket Force University of Engineering,2024,38(3):45-50,59.
[8]Ben Hamida A,Benoit A,Lambert P,et al.3-D deep learning approach for remote sensing image classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2018,56(8):4420-4434.
[9]Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need[C]//Advances in Neural Information Processing Systems. Long Beach:Curran Associates,2017:5998-6008.
[10]赵晶钰，李敏，陈谢发，等．融合注意力机制与全局信息的SAR舰船目标检测算法[J]．火箭军工程大学学报，2024,38(4):40-46.Zhao Jingyu,Li Min,Chen Xiefa,et al.SAR ship target detection algorithm combining attention mechanism and global information[J].Journal of Rocket Force University of Engineering,2024,38(4):40-46.
[11]Dosovitskiy A,Beyer L,Kolesnikov A,et al.An image is worth 16×16 words:transformers for image recognition at scale[EB/OL].(2021-06-03)[2026-03-27].https：//doi.org/10.48550/arXiv.2010.11929.
[12]Hong Danfeng,Han Zhu,Yao Jing,et al.SpectralFormer:rethinking hyperspectral image classification with transformers[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,60:5518615.
[13]Yang Xiaofei,Cao Weijia,Lu Yao,et al.Hyperspectral image transformer classification networks[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:5528715.
[14]Ahmad M, Shabbir S, Roy S K, et al. Hyperspectral image classification:traditional to deep models:a survey for future prospects[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:968-999.
[15]Shi Haotian,Luo Zihang,Ma Yiyang,et al.SSGTN:spectral spatial graph transformer network for hyperspectral image classification[J]. Remote Sensing,2026,18(2):199.
[16]Zhao Xiaofeng,Ma Junyi,Wang Lei,et al.GTCFN:a graph-based transformer and convolution fusion network for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2025,63:5530819.
[17]Chen Yuanjiang, Yang Bin, Bian Taonian, et al.Dual-scale graph transformer with spectral-spatial convolution for hyperspectral image classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2026,19:12430-12444.
[18]Zhang Zilin, Yu Haoyang, Jiang Zhaohui, et al.CentralGraphFormer:center-guided spectral spatial graph transformer for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2026,64:5507918.
[19]Kipf T N,Welling M.Semi-supervised classification with graph convolutional networks[EB/OL].(2017-02-22)[2026-03-27].https：//doi.org/10.48550/arXiv.1609.02907.
[20]Qin Anyong, Shang Zhaowei, Tian Jinyu, et al.Spectral spatial graph convolutional networks for semisupervised hyperspectral image classification[J].IEEE Geoscience and Remote Sensing Letters,2019,16(2):241-245.
[21]Hong Danfeng,Gao Lianru,Yao Jing,et al.Graph convolutional networks for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2021,59(7):5966-5978.
[22]Wan Sheng,Gong Chen,Zhong Ping,et al.Multiscale dynamic graph convolutional network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2020,58(5):3162-3177.
[23]赵晓枫，段永屹，马鋆懿，等．多尺度卷积与超像素级图卷积融合的高光谱图像分类网络[J]．火箭军工程大学学报，2025,39(5):94-106.Zhao Xiaofeng, Duan Yongyi, Ma Junyi, et al.Multiscale-convolutional and superpixel-level graph convolutional fusion network for hyperspectral image classification[J]. Journal of Rocket Force University of Engineering,2025,39(5):94-106.
[24]Ding Yao,Zhao Xiaofeng,Zhang Zhili,et al.Semisupervised locality preserving dense graph neural network with ARMA filters and context-aware learning for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-12.
[25]Jing Haoyu,Wu Sensen,Zhang Laifu,et al.Aggregative and contrastive dual-view graph attention network for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2024,62:5530817.
[26]Yang Aitao, Li Min, Ding Yao, et al. GTFN:GCN and transformer fusion network with spatialspectral features for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2023,61:6600115.
[27]Li Qimai,Han Zhichao,Wu Xiaoming.Deeper insights into graph convolutional networks for semisupervised learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.New Orleans:AAAI Press,2018,32(1):3538-3545.
[28]Luo Xingwen, Tu Bing, Liu Bo, et al. Hyperspectral image classification via dynamic adaptive graph convolutional network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2026, 64:5507818.
[29]Zhang Hao,Ku Junhua,Zhao Jie.Multi-scale graph wavelet convolutional network for hyperspectral image classification[J]. Frontiers in Remote Sensing,2025,6:1637820.
[30]Woo S,Park J,Lee J Y,et al.CBAM:convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision.Cham:Springer,2018:3-19.
[31]Song Weiwei,Li Shutao,Fang Leyuan,et al.Hyperspectral image classification with deep feature fusion network[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(6):3173-3184.
[32]Zhu Minghao,Jiao Licheng,Liu Fang,et al.Residual spectral-spatial attention network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2021,59(1):449-462.
[33]Li Rui,Zheng Shunyi,Duan Chenxi,et al.Classification of hyperspectral image based on doublebranch dual-attention mechanism network[J]. Remote Sensing,2020,12(3):582.
[34]Dong Yanni,Liu Quanwei,Du Bo,et al.Weighted feature fusion of convolutional neural network and graph attention network for hyperspectral image classification[J]. IEEE Transactions on Image Processing,2022,31:1559-1572.
[35]Zhou Hao,Luo Fulin,Zhuang Huiping,et al.Attention multihop graph and multiscale convolutional fusion network for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2023,61:5508614.
[36]Sun Le,Zhao Guangrui,Zheng Yuhui,et al.Spectral-spatial feature tokenization transformer for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022,60:5522214.
[37]Mei Shaohui,Song Chao,Ma Mingyang,et al.Hyperspectral image classification using group-aware hierarchical transformer[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:5539014.
Basic Information:
DOI：10.20189/j.cnki.CN/61-1527/E.202603005
China Classification Code:TP751;TP18
Citation Information:
[1]ZHOU Zhengyang,LI Wenhao,WANG Nian ,et al.Adaptive Multi-Hop Graph Convolution and Transformer Fusion Network for Hyperspectral Image Classification[J].Journal of Rocket Force University of Engineering,2026,40(03):69-79.DOI:10.20189/j.cnki.CN/61-1527/E.202603005.
2026-04-03
2026
2026-05-08
2026-05-18
2026
1
2026-06-15
2026-06-15