{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T14:04:49Z","timestamp":1769522689779,"version":"3.49.0"},"reference-count":55,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32271880"],"award-info":[{"award-number":["32271880"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["232102211048"],"award-info":[{"award-number":["232102211048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Henan Province Science and Technology Breakthrough Project","award":["32271880"],"award-info":[{"award-number":["32271880"]}]},{"name":"Henan Province Science and Technology Breakthrough Project","award":["232102211048"],"award-info":[{"award-number":["232102211048"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have led to promising advancements in hyperspectral image (HSI) classification; however, traditional CNNs with fixed square convolution kernels are insufficiently flexible to handle irregular structures. Similarly, GCNs that employ superpixel nodes instead of pixel nodes may overlook pixel-level features; both networks tend to extract features locally and cause loss of multilayer contextual semantic information during feature extraction due to the fixed kernel. To leverage the strengths of CNNs and GCNs, we propose a multiscale pixel-level and superpixel-level (MPAS)-based HSI classification method. The network consists of two sub-networks for extracting multi-level information of HSIs: a multi-scale hybrid spectral\u2013spatial attention convolution branch (HSSAC) and a parallel multi-hop graph convolution branch (MGCN). HSSAC comprehensively captures pixel-level features with different kernel sizes through parallel multi-scale convolution and cross-path fusion to reduce the semantic information loss caused by fixed convolution kernels during feature extraction and learns adjustable weights from the adaptive spectral\u2013spatial attention module (SSAM) to capture pixel-level feature correlations with less computation. MGCN can systematically aggregate multi-hop contextual information to better model HSIs\u2019 spatial background structure using the relationship between parallel multi-hop graph transformation nodes. The proposed MPAS effectively captures multi-layer contextual semantic features by leveraging pixel-level and superpixel-level spectral\u2013spatial information, which improves the performance of the HSI classification task while ensuring computational efficiency. Extensive evaluation experiments on three real-world HSI datasets demonstrate that MPAS outperforms other state-of-the-art networks, demonstrating its superior feature learning capabilities.<\/jats:p>","DOI":"10.3390\/rs15174235","type":"journal-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T08:51:14Z","timestamp":1693299074000},"page":"4235","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Multiscale Pixel-Level and Superpixel-Level Method for Hyperspectral Image Classification: Adaptive Attention and Parallel Multi-Hop Graph Convolution"],"prefix":"10.3390","volume":"15","author":[{"given":"Junru","family":"Yin","sequence":"first","affiliation":[{"name":"College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"}]},{"given":"Xuan","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"}]},{"given":"Ruixia","family":"Hou","sequence":"additional","affiliation":[{"name":"Research Institute of Resource Information Techniques, CAF, Beijing 100091, China"}]},{"given":"Qiqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0095-1354","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"}]},{"given":"Aiguang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"key":"ref_1","first-page":"102603","article-title":"Hyperspectral image classification on insufficient-sample and feature learning using deep neural networks: A review","volume":"105","author":"Wambugu","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.neucom.2021.03.035","article-title":"A survey: Deep learning for hyperspectral image classification with few labeled samples","volume":"448","author":"Jia","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.isprsjprs.2023.01.024","article-title":"From center to surrounding: An interactive learning framework for hyperspectral image classification","volume":"197","author":"Yang","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1109\/TIP.2023.3243853","article-title":"Single-source domain expansion network for cross-scene hyperspectral image classification","volume":"32","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5507113","DOI":"10.1109\/TGRS.2023.3258977","article-title":"Classification via structure-preserved hypergraph convolution network for hyperspectral image","volume":"61","author":"Duan","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1016\/j.neucom.2022.05.093","article-title":"Multi-view learning for hyperspectral image classification: An overview","volume":"500","author":"Li","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Liang, N., Duan, P., Xu, H., and Cui, L. (2022). Multi-view structural feature extraction for hyperspectral image classification. Remote Sens., 14.","DOI":"10.3390\/rs14091971"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6690","DOI":"10.1109\/TGRS.2019.2907932","article-title":"Deep learning for hyperspectral image classification: An overview","volume":"57","author":"Li","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3185","DOI":"10.1109\/TCYB.2020.3004263","article-title":"Spectral\u2013spatial weighted kernel manifold embedded distribution alignment for remote sensing image classification","volume":"51","author":"Dong","year":"2020","journal-title":"IEEE Trans. Cybern."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5502713","DOI":"10.1109\/TGRS.2023.3241097","article-title":"Multiscale diff-changed feature fusion network for hyperspectral image change detection","volume":"61","author":"Luo","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3232","DOI":"10.1109\/TGRS.2019.2951160","article-title":"Spectral\u2013spatial attention network for hyperspectral image classification","volume":"58","author":"Sun","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3336053","article-title":"Multiscanning-Based RNN-Transformer for Hyperspectral Image Classification","volume":"61","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5502105","DOI":"10.1109\/LGRS.2023.3248582","article-title":"Double Attention Transformer for Hyperspectral Image Classification","volume":"20","author":"Tang","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_14","first-page":"1","article-title":"Self-supervised learning with adaptive distillation for hyperspectral image classification","volume":"60","author":"Yue","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xie, E., Chen, N., Peng, J., Sun, W., Du, Q., and You, X. (2023). Semantic and spatial\u2013spectral feature fusion transformer network for the classification of hyperspectral image. CAAI Trans. Intell. Technol.","DOI":"10.1049\/cit2.12201"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","article-title":"ML-KNN: A lazy learning approach to multi-label learning","volume":"40","author":"Zhang","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/TIP.2013.2293423","article-title":"Gradient magnitude similarity deviation: A highly efficient perceptual image quality index","volume":"23","author":"Xue","year":"2013","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/TGRS.2017.2754511","article-title":"Local binary pattern-based hyperspectral image classification with superpixel guidance","volume":"56","author":"Jia","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1049\/cje.2021.03.010","article-title":"Color Context Binary Pattern Using Progressive Bit Correction for Image Classification","volume":"30","author":"Song","year":"2021","journal-title":"Chin. J. Electron."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8813","DOI":"10.1109\/TGRS.2019.2923213","article-title":"3-D Gaussian\u2013Gabor feature extraction and selection for hyperspectral imagery classification","volume":"57","author":"Jia","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random forest in remote sensing: A review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2387","DOI":"10.1109\/TNNLS.2019.2935608","article-title":"Domain adaptation with neural embedding matching","volume":"31","author":"Wang","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11093","DOI":"10.1109\/TCYB.2021.3070909","article-title":"Asymmetric weighted logistic metric learning for hyperspectral target detection","volume":"52","author":"Dong","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2381","DOI":"10.1109\/JSTARS.2015.2388577","article-title":"Spectral\u2013spatial classification of hyperspectral data based on deep belief network","volume":"8","author":"Chen","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3231215","article-title":"Multi-structure KELM with attention fusion strategy for hyperspectral image classification","volume":"60","author":"Sun","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","first-page":"1","article-title":"MSLAN: A Two-Branch Multidirectional Spectral-Spatial LSTM Attention Network for Hyperspectral Image Classification","volume":"60","author":"Song","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1109\/TNNLS.2020.3029523","article-title":"Multilayer spectral\u2013spatial graphs for label noisy robust hyperspectral image classification","volume":"33","author":"Jiang","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1109\/TGRS.2018.2861992","article-title":"Hyperspectral image classification in the presence of noisy labels","volume":"57","author":"Jiang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5501205","DOI":"10.1109\/LGRS.2023.3236672","article-title":"Hierarchical Feature Fusion and Selection for Hyperspectral Image Classification","volume":"20","author":"Feng","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"6232","DOI":"10.1109\/TGRS.2016.2584107","article-title":"Deep feature extraction and classification of hyperspectral images based on convolutional neural networks","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"7570","DOI":"10.1109\/JSTARS.2021.3099118","article-title":"Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks","volume":"14","author":"Ghaderizadeh","year":"2021","journal-title":"IEEE J. Sel. Top Appl. Earth Obs. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ge, H., Wang, L., Liu, M., Zhu, Y., Zhao, X., Pan, H., and Liu, Y. (2023). Two-Branch Convolutional Neural Network with Polarized Full Attention for Hyperspectral Image Classification. Remote Sens., 15.","DOI":"10.3390\/rs15030848"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"5401","DOI":"10.1109\/JSTARS.2022.3187009","article-title":"Multiscale DenseNet meets with bi-RNN for hyperspectral image classification","volume":"15","author":"Liang","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"7831","DOI":"10.1109\/TGRS.2020.3043267","article-title":"Attention-based adaptive spectral-spatial kernel resnet for hyperspectral image classification","volume":"59","author":"Roy","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3231215","article-title":"Spectral\u2013spatial feature tokenization transformer for hyperspectral image classification","volume":"60","author":"Sun","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","unstructured":"Bruna, J., Zaremba, W., Szlam, A., and LeCun, Y. (2014). Spectral networks and deep locally connected networks on graphs. arXiv."},{"key":"ref_37","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_38","unstructured":"Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019). Simplifying graph convolutional networks. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1109\/LGRS.2018.2869563","article-title":"Spectral\u2013spatial graph convolutional networks for semisupervised hyperspectral image classification","volume":"16","author":"Qin","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3162","DOI":"10.1109\/TGRS.2019.2949180","article-title":"Multiscale dynamic graph convolutional network for hyperspectral image classification","volume":"58","author":"Wan","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"5966","DOI":"10.1109\/TGRS.2020.3015157","article-title":"Graph convolutional networks for hyperspectral image classification","volume":"59","author":"Hong","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"8657","DOI":"10.1109\/TGRS.2020.3037361","article-title":"CNN-enhanced graph convolutional network with pixel-and superpixel-level feature fusion for hyperspectral image classification","volume":"59","author":"Liu","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1109\/TIP.2022.3144017","article-title":"Weighted feature fusion of convolutional neural network and graph attention network for hyperspectral image classification","volume":"31","author":"Dong","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"4208","DOI":"10.1080\/10106049.2021.1882006","article-title":"A new deep learning approach for classification of hyperspectral images: Feature and decision level fusion of spectral and spatial features in multiscale CNN","volume":"37","author":"Sharifi","year":"2022","journal-title":"Geocarto Int."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1049\/cje.2021.00.130","article-title":"Hyperspectral Image Classification Based on A Multi-Scale Weighted Kernel Network","volume":"31","author":"Sun","year":"2022","journal-title":"Chin. J. Electron."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Xue, H., Sun, X.K., and Sun, W.X. (2020, January 19\u201322). Multi-hop hierarchical graph neural networks. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Republic of Korea.","DOI":"10.1109\/BigComp48618.2020.00-95"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Yang, Y., Tang, X., Zhang, X., Ma, J., Liu, F., Jia, X., and Jiao, L. (IEEE Trans. Neural Netw. Learn Syst., 2022). Semi-supervised multiscale dynamic graph convolution network for hyperspectral image classification, IEEE Trans. Neural Netw. Learn Syst., ahead of print.","DOI":"10.1109\/TNNLS.2022.3212985"},{"key":"ref_48","unstructured":"Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"Achanta","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_50","first-page":"751","article-title":"SSCDenseNet: A spectral-spatial convolutional dense network for hyperspectral image classification","volume":"48","author":"Liu","year":"2020","journal-title":"Acta Electron. Sin."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_52","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., and Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Li, R., Zheng, S., Duan, C., Yang, Y., and Wang, X. (2020). Classification of hyperspectral image based on double-branch dual-attention mechanism network. Remote Sens., 12.","DOI":"10.20944\/preprints201912.0059.v2"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Ma, W., Yang, Q., Wu, Y., Zhao, W., and Zhang, X. (2019). Double-branch multi-attention mechanism network for hyperspectral image classification. Remote Sens., 11.","DOI":"10.3390\/rs11111307"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Wang, W., Dou, S., Jiang, Z., and Sun, L. (2018). A fast dense spectral\u2013spatial convolution network framework for hyperspectral images classification. Remote Sens., 10.","DOI":"10.3390\/rs10071068"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/17\/4235\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:41:29Z","timestamp":1760128889000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/17\/4235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,29]]},"references-count":55,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["rs15174235"],"URL":"https:\/\/doi.org\/10.3390\/rs15174235","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,29]]}}}