{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T20:46:21Z","timestamp":1774730781970,"version":"3.50.1"},"reference-count":60,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:00:00Z","timestamp":1725753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Military Science and Technology Commission of the Communist Party Central Committee (CSTC) Foundation Strengthening Program","award":["JKWATR-210503"],"award-info":[{"award-number":["JKWATR-210503"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Synthetic Aperture Radar (SAR) enables the acquisition of high-resolution imagery even under severe meteorological and illumination conditions. Its utility is evident across a spectrum of applications, particularly in automatic target recognition (ATR). Since SAR samples are often scarce in practical ATR applications, there is an urgent need to develop sample-efficient augmentation techniques to augment the SAR images. However, most of the existing generative approaches require an excessive amount of training samples for effective modeling of the SAR imaging characteristics. Additionally, they show limitations in augmenting the interesting target samples while maintaining image recognizability. In this study, we introduce an innovative single-sample image generation approach tailored to SAR data augmentation. To closely approximate the target distribution across both the spatial layout and local texture, a multi-level Generative Adversarial Network (GAN) architecture is constructed. It comprises three distinct GANs that independently model the structural, semantic, and texture patterns. Furthermore, we introduce multiple constraints including prior-regularized noise sampling and perceptual loss optimization to enhance the fidelity and stability of the generation process. Comparative evaluations against the state-of-the-art generative methods demonstrate the superior performance of the proposed method in terms of generation diversity, recognizability, and stability. In particular, its advantages over the baseline method are up to 0.2 and 0.22 in the SIFID and SSIM, respectively. It also exhibits stronger robustness in the generation of images across varying spatial sizes.<\/jats:p>","DOI":"10.3390\/rs16173326","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T04:15:01Z","timestamp":1725855301000},"page":"3326","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Coarse-to-Fine Structure and Semantic Learning for Single-Sample SAR Image Generation"],"prefix":"10.3390","volume":"16","author":[{"given":"Xilin","family":"Wang","sequence":"first","affiliation":[{"name":"Xi\u2019an Electronic Engineering Research Institute, China North Industries Group Corporation Limited, Xi\u2019an 710100, China"}]},{"given":"Bingwei","family":"Hui","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Xi\u2019an Electronic Engineering Research Institute, China North Industries Group Corporation Limited, Xi\u2019an 710100, China"}]},{"given":"Rubo","family":"Jin","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0653-8373","authenticated-orcid":false,"given":"Lei","family":"Ding","sequence":"additional","affiliation":[{"name":"Key Laboratory of Remote Sensing and Digital Earth, Chinese Academy of Sciences Aerospace Information Research Institute, Beijing 100094, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"94415","DOI":"10.1109\/ACCESS.2023.3310539","article-title":"A Deep-Learning-Based Lightweight Model for Ship Localizations in SAR Images","volume":"11","author":"Bhattacharjee","year":"2023","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/JOE.1980.1145459","article-title":"An initial assessment of the performance achieved by the Seasat-1 radar altimeter","volume":"5","author":"Townsend","year":"1980","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_3","first-page":"5216913","article-title":"Reinforcement Learning for SAR Target Orientation Inference with the Differentiable SAR Renderer","volume":"62","author":"Wang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1109\/36.406668","article-title":"Overview of results of Spaceborne Imaging Radar-C, X-Band Synthetic Aperture Radar (SIR-C\/X-SAR)","volume":"33","author":"Stofan","year":"1995","journal-title":"IEEE Trans. Geosci. Remote"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, S., Zhan, R., Wang, W., and Zhang, J. (2022). LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection. Remote Sens., 14.","DOI":"10.3390\/rs14194801"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4408","DOI":"10.1109\/JSTARS.2024.3358449","article-title":"Novel Category Discovery Without Forgetting for Automatic Target Recognition","volume":"17","author":"Huang","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_7","first-page":"5202813","article-title":"SAR target incremental recognition based on features with strong separability","volume":"62","author":"Gao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4000605","DOI":"10.1109\/LGRS.2023.3337143","article-title":"Conditional Diffusion for SAR to Optical Image Translation","volume":"21","author":"Bai","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/TGRS.2016.2551720","article-title":"Target Classification Using the Deep Convolutional Networks for SAR Images","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, H., Chen, S., Tao, M., and Wei, J. (2024). A Two-Stage SAR Image Generation Algorithm Based on GAN with Reinforced Constraint Filtering and Compensation Techniques. Remote Sens., 16.","DOI":"10.3390\/rs16111963"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ding, Z., Wang, Z., Wei, Y., Li, L., Ma, X., Zhang, T., and Zeng, T. (2022). SPA-GAN: SAR Parametric Autofocusing Method with Generative Adversarial Network. Remote Sens., 14.","DOI":"10.3390\/rs14205159"},{"key":"ref_12","first-page":"4011005","article-title":"A high-quality multicategory SAR images generation method with multiconstraint GAN for ATR","volume":"19","author":"Du","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","first-page":"104028","article-title":"SAR vehicle image generation with integrated deep imaging geometric information","volume":"132","author":"Sun","year":"2024","journal-title":"Int. J. Appl. Earth Observ. Geoinf."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kuang, Y., Ma, F., Li, F., Liu, F., and Zhang, F. (2023). Semantic-Layout-Guided Image Synthesis for High-Quality Synthetic-Aperature Radar Detection Sample Generation. Remote Sens., 15.","DOI":"10.3390\/rs15245654"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"217554","DOI":"10.1109\/ACCESS.2020.3042213","article-title":"K-Means clustering guided generative adversarial networks for SAR-optical image matching","volume":"8","author":"Du","year":"2020","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Harrison, R.W. (2022). Continuous restricted Boltzmann machines. Wirel. Netw., 1263\u20131267.","DOI":"10.1007\/s11276-018-01903-6"},{"key":"ref_17","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hui, L. (2024). Research on Medical Image Enhancement Method Based on Conditional Entropy Generative Adversarial Networks. Appl. Math. Nonlinear Sci., 9.","DOI":"10.2478\/amns-2024-0337"},{"key":"ref_19","first-page":"2488","article-title":"Application of SAR Ship Data Augmentation Based on Generative Adversarial Network in Improved SSD","volume":"40","author":"Yang","year":"2019","journal-title":"Acta Armamentarii"},{"key":"ref_20","unstructured":"Jaskie, K., Dezember, M., and Majumder, U.K. (May, January 30). VAE for SAR active learning. Proceedings of the Algorithms for Synthetic Aperture Radar Imagery XXX, Orlando, FL, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, M., Zhang, P., Zhang, Y., Yang, M., Li, X., Dong, X., and Yang, L. (2024). SAR-to-Optical Image Translation via an Interpretable Network. Remote Sens., 16.","DOI":"10.3390\/rs16020242"},{"key":"ref_22","unstructured":"Barratt, S., and Sharma, R. (2018). A Note on the Inception Score. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105239","DOI":"10.1016\/j.jappgeo.2023.105239","article-title":"Facies conditional simulation based on VAE-GAN model and image quilting algorithm","volume":"219","author":"Zhao","year":"2023","journal-title":"J. Appl. Geophys."},{"key":"ref_24","unstructured":"Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive Growing of GANs for Improved Quality, Stability, and Variation. arXiv."},{"key":"ref_25","unstructured":"Dalva, Y., Yesiltepe, H., and Yanardag, P. (2024). GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Shocher, A., Cohen, N., and Irani, M. (2018, January 18\u201322). Zero-Shot Super-Resolution Using Deep Internal Learning(Conference Paper). Proceedings of the IEEE Computer Society Conference On Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00329"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Shabtay, N., Schwartz, E., and Giryes, R. (2024). Deep Phase Coded Image Prior. arXiv.","DOI":"10.1109\/ICCP61108.2024.10645026"},{"key":"ref_28","unstructured":"Shocher, A., Bagon, S., Isola, P.J., and Irani, M. (November, January 27). InGAN: Capturing and Retargeting the \u201cDNA\u201d of a Natural Image. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shaham, T.R., Dekel, T., and Michaeli, T. (2019). SinGAN: Learning a Generative Model from a Single Natural Image. arXiv.","DOI":"10.1109\/ICCV.2019.00467"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hinz, T., Fisher, M., Wang, O., and Wermter, S. (2021, January 3\u20137). Improved Techniques for Training Single-Image GANs. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00134"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"149808","DOI":"10.1109\/ACCESS.2020.3016780","article-title":"COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data","volume":"8","author":"Horry","year":"2020","journal-title":"IEEE Access"},{"key":"ref_32","unstructured":"Gur, S., Benaim, S., and Wolf, L. (2020). Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"154671","DOI":"10.1016\/j.jcrc.2024.154671","article-title":"Ventilator-associated event (VAE) epidemiology and prognosis: Preliminary results of VAE-T\u00fcrkiye","volume":"81","author":"Senbayrak","year":"2024","journal-title":"J. Crit. Care"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, J., Xu, Q., Kang, Q., and Zhou, M. (2023). MOGAN: Morphologic-Structure-Aware Generative Learning From a Single Image. arXiv.","DOI":"10.1109\/TSMC.2023.3331227"},{"key":"ref_35","unstructured":"Zhang, Z., Han, C., and Guo, T. (2022). ExSinGAN: Learning an Explainable Generative Model from a Single Image. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1109\/LGRS.2017.2699196","article-title":"Synthetic Aperture Radar Image Synthesis by Using Generative Adversarial Nets","volume":"14","author":"Guo","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gao, F., Yang, Y., Wang, J., Sun, J., Yang, E., and Zhou, H. (2018). A Deep Convolutional Generative Adversarial Networks (DCGANs)-Based Semi-Supervised Method for Object Recognition in Synthetic Aperture Radar (SAR) Images. Remote Sens., 10.","DOI":"10.3390\/rs10060846"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Oghim, S., Kim, Y., Bang, H., Lim, D., and Ko, J. (2024). SAR Image Generation Method Using DH-GAN for Automatic Target Recognition. Sensors, 24.","DOI":"10.3390\/s24020670"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, C., Zhang, H., Dong, Y., and Wei, S. (2019). A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds. Remote Sens., 11.","DOI":"10.3390\/rs11070765"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"113522","DOI":"10.1016\/j.rse.2023.113522","article-title":"GAN-based SAR and optical image translation for wildfire impact assessment using multi-source remote sensing data","volume":"289","author":"Hu","year":"2023","journal-title":"Remote Sens. Environ."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Menouar, H., and Hamila, R. (2024, January 27\u201329). Multimodal Crowd Counting with Pix2Pix GANs. Proceedings of the 19th International Conference on Computer Vision Theory and Applications, Rome, Italy.","DOI":"10.5220\/0012547900003660"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/j.cja.2020.08.035","article-title":"Advanced high-order nonlinear chirp scaling algorithm for high-resolution wide-swath spaceborne SAR","volume":"34","author":"Men","year":"2021","journal-title":"Chin. J. Aeronaut."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"120234","DOI":"10.1109\/ACCESS.2020.3005861","article-title":"HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance Segmentation","volume":"8","author":"Wei","year":"2020","journal-title":"IEEE Access"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Golhar, M.V., Bobrow, T.L., Ngamruengphong, S., and Durr, N.J. (2024). GAN Inversion for Data Augmentation to Improve Colonoscopy Lesion Classification. IEEE J. Biomed. Health Inform.","DOI":"10.1109\/JBHI.2024.3397611"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"127828","DOI":"10.1016\/j.neucom.2024.127828","article-title":"MAFormer: A transformer network with multi-scale attention fusion for visual recognition","volume":"595","author":"Sun","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"5204516","DOI":"10.1109\/TGRS.2024.3361931","article-title":"Target Recognition for SAR Images Enhanced by Polarimetric Information","volume":"62","author":"Lin","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_47","unstructured":"Simonyan, K. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_48","unstructured":"Ghazanfari, S., Garg, S., Krishnamurthy, P., Khorrami, F., and Araujo, A. (2023). R-LPIPS: An Adversarially Robust Perceptual Similarity Metric. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Jiang, N., Zhao, W., Wang, H., Luo, H., Chen, Z., and Zhu, J. (2024). Lightweight Super-Resolution Generative Adversarial Network for SAR Images. Remote Sens., 16.","DOI":"10.3390\/rs16101788"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1080\/10255842.2022.2102422","article-title":"A novel sEMG data augmentation based on WGAN-GP","volume":"26","author":"Coelho","year":"2023","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1016\/j.procs.2022.08.067","article-title":"BigGAN evaluation for the generation of vehicle interior images","volume":"204","author":"Dixe","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Deijn, R., Batra, A., Koch, B., Mansoor, N., and Makkena, H. (2024). Reviewing FID and SID Metrics on Generative Adversarial Networks. arXiv.","DOI":"10.5121\/csit.2024.140208"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"e75485","DOI":"10.7554\/eLife.75485","article-title":"One-shot generalization in humans revealed through a drawing task","volume":"11","author":"Tiedemann","year":"2022","journal-title":"eLife"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_55","unstructured":"Xiang, P., Xiang, S., and Zhao, Y. (2023). Texturize a GAN Using a Single Image. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"100250","DOI":"10.1016\/j.jnlest.2024.100250","article-title":"Data augmentation method for insulators based on Cycle GAN","volume":"22","author":"Ye","year":"2024","journal-title":"J. Electron. Sci. Technol."},{"key":"ref_57","unstructured":"Boutin, V., Singhal, L., Thomas, X., and Serre, T. (2022). Diversity vs. Recognizability: Human-like generalization in one-shot generative models. arXiv."},{"key":"ref_58","unstructured":"Rumelhart, D.E., and McClelland, J.L. (1987). Information Processing in Dynamical Systems: Foundations of Harmony Theory, MIT Press."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"21503","DOI":"10.1109\/ACCESS.2024.3359689","article-title":"Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams","volume":"12","author":"Ramzan","year":"2024","journal-title":"IEEE Access"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"105938","DOI":"10.1016\/j.envsoft.2023.105938","article-title":"SSIMS-Flow: Image velocimetry workbench for open-channel flow rate estimation","volume":"173","year":"2024","journal-title":"Environ. Model. Softw."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/17\/3326\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:51:26Z","timestamp":1760111486000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/17\/3326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,8]]},"references-count":60,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["rs16173326"],"URL":"https:\/\/doi.org\/10.3390\/rs16173326","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,8]]}}}