{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:33:20Z","timestamp":1776101600295,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T00:00:00Z","timestamp":1672099200000},"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":["62071336"],"award-info":[{"award-number":["62071336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The expensive acquisition of labeled data limits the practical use of supervised learning on polarimetric synthetic aperture radar (PolSAR) image analysis. Semi-supervised learning has attracted considerable attention as it can utilize few labeled data and very many unlabeled data. The scattering response of PolSAR data is strongly spatial distribution dependent, which provides rich information about land-cover properties. In this paper, we propose a semi-supervised learning method named multi-domain fusion graph network (MDFGN) to explore the multi-domain fused features including spatial domain and feature domain. Three major factors strengthen the proposed method for PolSAR image analysis. Firstly, we propose a novel sample selection criterion to select reliable unlabeled data for training set expansion. Multi-domain fusion graph is proposed to improve the feature diversity by extending the sample selection from the feature domain to the spatial-feature fusion domain. In this way, the selecting accuracy is improved. By few labeled data, very many accurate unlabeled data are obtained. Secondly, multi-model triplet encoder is proposed to achieve superior feature extraction. Equipped with triplet loss, limited training samples are fully utilized. For expanding training samples with different patch sizes, multiple models are obtained for the fused classification result acquisition. Thirdly, multi-level fusion strategy is proposed to apply different image patch sizes for different expanded training data and obtain the fused classification result. The experiments are conducted on Radarsat-2 and AIRSAR images. With few labeled samples (about 0.003\u20130.007%), the overall accuracy of the proposed method ranges between 94.78% and 99.24%, which demonstrates the proposed method\u2019s robustness and excellence.<\/jats:p>","DOI":"10.3390\/rs15010160","type":"journal-article","created":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T05:30:27Z","timestamp":1672205427000},"page":"160","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-Domain Fusion Graph Network for Semi-Supervised PolSAR Image Classification"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0738-1013","authenticated-orcid":false,"given":"Rui","family":"Tang","sequence":"first","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan 430079, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1490-0347","authenticated-orcid":false,"given":"Fangling","family":"Pu","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan 430079, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1783-9051","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan 430079, China"}]},{"given":"Zhaozhuo","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan 430079, China"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan 430079, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/LGRS.2015.2499239","article-title":"Deep learning earth observation classification using ImageNet pretrained networks","volume":"13","author":"Marmanis","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MGRS.2017.2762307","article-title":"Deep learning in remote sensing: A comprehensive review and list of resources","volume":"5","author":"Zhu","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_3","first-page":"8740","article-title":"Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler","volume":"34","author":"Desai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"129136","DOI":"10.1109\/ACCESS.2019.2939649","article-title":"SAR-to-Optical Image Translation Using Supervised Cycle-Consistent Adversarial Networks","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5777","DOI":"10.1109\/TGRS.2017.2714169","article-title":"Copula-Based Joint Statistical Model for Polarimetric Features and Its Application in PolSAR Image Classification","volume":"55","author":"Dong","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","first-page":"1","article-title":"Composite Sequential Network with POA Attention for PolSAR Image Analysis","volume":"60","author":"Yang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1109\/LGRS.2016.2618840","article-title":"Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks","volume":"13","author":"Zhou","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gao, F., Huang, T., Wang, J., and Sun, J. (2017). Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image Classification. Appl. Sci., 7.","DOI":"10.3390\/app7050447"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"7177","DOI":"10.1109\/TGRS.2017.2743222","article-title":"Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification","volume":"55","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.3390\/rs10121984","article-title":"A Novel Deep Fully Convolutional Network for PolSAR Image Classification","volume":"10","author":"Li","year":"2018","journal-title":"Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.3390\/rs11222653","article-title":"Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network","volume":"11","author":"Cao","year":"2019","journal-title":"Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"415","DOI":"10.3390\/rs11040415","article-title":"Adversarial Reconstruction-Classification Networks for PolSAR Image Classification","volume":"11","author":"Chen","year":"2019","journal-title":"Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5300","DOI":"10.1109\/JSTARS.2019.2956650","article-title":"PolSARNet: A Deep Fully Convolutional Network for Polarimetric SAR Image Classification","volume":"12","author":"Mullissa","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.isprsjprs.2019.03.015","article-title":"A new fully convolutional neural network for semantic segmentation of polarimetric SAR imagery in complex land cover ecosystem","volume":"151","author":"Mohammadimanesh","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"He, C., Tu, M., Xiong, D., and Liao, M. (2020). Nonlinear manifold learning integrated with fully convolutional networks for polSAR image classification. Remote Sens., 12.","DOI":"10.3390\/rs12040655"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4493","DOI":"10.1109\/JSTARS.2020.3014966","article-title":"A New Parallel Dual-Channel Fully Convolutional Network via Semi-Supervised FCM for PolSAR Image Classification","volume":"13","author":"Zhao","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102083","DOI":"10.1016\/j.rcim.2020.102083","article-title":"A new graph-based semi-supervised method for surface defect classification","volume":"68","author":"Wang","year":"2021","journal-title":"Robot. Comput. -Integr. Manuf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1109\/TCSI.2020.2991645","article-title":"A Semi-Supervised Learning Approach for Identification of Piecewise Affine Systems","volume":"67","author":"Du","year":"2020","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"8583","DOI":"10.1109\/TGRS.2020.2988982","article-title":"Semi-Supervised PolSAR Image Classification Based on Improved Tri-Training With a Minimum Spanning Tree","volume":"58","author":"Wang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Du, L., Wang, Y., and Xie, W. (August, January 28). A semi-supervised method for sar target discrimination based on co-training. Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2019), Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8898369"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102444","DOI":"10.1016\/j.ipm.2020.102444","article-title":"A Selection Metric for semi-supervised learning based on neighborhood construction","volume":"58","author":"Emadi","year":"2021","journal-title":"Inf. Process. Manag."},{"key":"ref_22","first-page":"5511812","article-title":"Semi-Supervised Locality Preserving Dense Graph Neural Network With ARMA Filters and Context-Aware Learning for Hyperspectral Image Classification","volume":"60","author":"Ding","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, Z., Liu, H., Wang, Y., and Hu, J. (2017). Generative Adversarial Networks-Based Semi-Supervised Learning for Hyperspectral Image Classification. Remote Sens., 9.","DOI":"10.3390\/rs9101042"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, H., Guan, C., and Chin, Z. (2007, January 7\u201313). A self-training semi-supervised support vector machine algorithm and its applications in brain computer interface. Proceedings of the International Conference on Acoustics Speech and Signal Processing ICASSP 2007, Toronto, ON, Canada.","DOI":"10.1109\/ICASSP.2007.366697"},{"key":"ref_25","first-page":"3967","article-title":"Tile2Vec: Unsupervised Representation Learning for Spatially Distributed Data","volume":"33","author":"Jean","year":"2019","journal-title":"Assoc. Adv. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","article-title":"Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs","volume":"42","author":"Malkov","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"Deep Metric Learning Using Triplet Network","volume":"9370","author":"Hoffer","year":"2015","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TGRS.2017.2748120","article-title":"Diversity-Promoting Deep Structural Metric Learning for Remote Sensing Scene Classification","volume":"56","author":"Gong","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5991","DOI":"10.1109\/TGRS.2019.2903794","article-title":"Dynamic Fractal Texture Analysis for PolSAR Land Cover Classification","volume":"57","author":"Yang","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2294","DOI":"10.1109\/TGRS.2020.3004858","article-title":"Hyperspectral Image Classification via Spatial Window-Based Multiview Intact Feature Learning","volume":"59","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"5504205","DOI":"10.1109\/LGRS.2021.3062944","article-title":"Graph Sample and Aggregate-Attention Network for Hyperspectral Image Classification","volume":"19","author":"Ding","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.neucom.2022.06.031","article-title":"Multi-feature fusion: Graph neural network and CNN combining for hyperspectral image classification","volume":"501","author":"Ding","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4561","DOI":"10.1109\/JSTARS.2021.3074469","article-title":"Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification","volume":"14","author":"Ding","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1109\/TIP.2021.3130528","article-title":"Scalable Distributed Hashing for Approximate Nearest Neighbor Search","volume":"31","author":"Cao","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_35","unstructured":"Ponomarenko, A., Mal\u2019kov, Y., Logvinov, A., and Krylov, V. (2011, January 12\u201314). Approximate Nearest Neighbor Search Small World Approach. Proceedings of the International Conference on Information and Communication Technologies & Applications, Azerbaijan, Baku."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1239\/jap\/1165505216","article-title":"Navigation in small-world networks: A scale-free continuum model","volume":"43","author":"Franceschetti","year":"2006","journal-title":"J. Appl. Probab."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1038\/nphys1130","article-title":"Navigability of complex networks","volume":"5","author":"Boguna","year":"2009","journal-title":"Nat. Phys."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"8905","DOI":"10.1109\/TGRS.2020.2991657","article-title":"Deep Metric Learning Based on Scalable Neighborhood Components for Remote Sensing Scene Characterization","volume":"58","author":"Kang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3840","DOI":"10.1109\/TGRS.2018.2888618","article-title":"Cross-Domain Distance Metric Learning Framework With Limited Target Samples for Scene Classification of Aerial Images","volume":"57","author":"Yan","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Penatti, O.A.B., Nogueira, K., and dos Santos, J.A. Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains? In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, USA, 7\u201312 June 2015.","DOI":"10.1109\/CVPRW.2015.7301382"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107610","DOI":"10.1016\/j.patcog.2020.107610","article-title":"Efficient densely connected convolutional neural networks","volume":"109","author":"Li","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Haensch, R., and Hellwich, O. (2018). Classification of PolSAR Images by Stacked Random Forests. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7020074"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Isuhuaylas, L.A.V., Hirata, Y., Ventura Santos, L.C., and Serrudo Torobeo, N. (2018). Natural Forest Mapping in the Andes (Peru): A Comparison of the Performance of Machine-Learning Algorithms. Remote Sens., 10.","DOI":"10.3390\/rs10050782"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Berhane, T.M., Lane, C.R., Wu, Q., Autrey, B.C., Anenkhonov, O.A., Chepinoga, V.V., and Liu, H. (2018). Decision-Tree, Rule-Based and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory. Remote Sens., 10.","DOI":"10.3390\/rs10040580"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Lu, X., Zhang, J., Li, T., and Zhang, Y. (2016). Incorporating Diversity into Self-Learning for Synergetic Classification of Hyperspectral and Panchromatic Images. Remote Sens., 8.","DOI":"10.3390\/rs8100804"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","article-title":"Tri-training: Exploiting unlabeled data using three classifiers","volume":"17","author":"Zhou","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_48","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/1\/160\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:53:10Z","timestamp":1760147590000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/1\/160"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,27]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["rs15010160"],"URL":"https:\/\/doi.org\/10.3390\/rs15010160","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,27]]}}}