{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T22:33:04Z","timestamp":1781821984307,"version":"3.54.5"},"reference-count":30,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T00:00:00Z","timestamp":1673568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation from Jiangsu Province","award":["BK20200420"],"award-info":[{"award-number":["BK20200420"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Mass production of high-quality synthetic SAR training imagery is essential for boosting the performance of deep-learning (DL)-based SAR automatic target recognition (ATR) algorithms in an open-world environment. To address this problem, we exploit both the widely used Moving and Stationary Target Acquisition and Recognition (MSTAR) SAR dataset and the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset, which consists of selected samples from the MSTAR dataset and their computer-generated synthetic counterparts. A series of data augmentation experiments are carried out. First, the sparsity of the scattering centers of the targets is exploited for new target pose synthesis. Additionally, training data with various clutter backgrounds are synthesized via clutter transfer, so that the neural networks are better prepared to cope with background changes in the test samples. To effectively augment the synthetic SAR imagery in the SAMPLE dataset, a novel contrast-based data augmentation technique is proposed. To improve the robustness of neural networks against out-of-distribution (OOD) samples, the SAR images of ground military vehicles collected by the self-developed MiniSAR system are used as the training data for the adversarial outlier exposure procedure. Simulation results show that the proposed data augmentation methods are effective in improving both the target classification accuracy and the OOD detection performance. The purpose of this work is to establish the foundation for large-scale, open-field implementation of DL-based SAR-ATR systems, which is not only of great value in the sense of theoretical research, but is also potentially meaningful in the aspect of military application.<\/jats:p>","DOI":"10.3390\/s23020941","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T05:30:07Z","timestamp":1673847007000},"page":"941","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Target Recognition in SAR Images by Deep Learning with Training Data Augmentation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5440-3556","authenticated-orcid":false,"given":"Zhe","family":"Geng","sequence":"first","affiliation":[{"name":"Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei-Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Nanjing Institute of Technology, Nanjing 211167, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dai-Yin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mason, E., Yonel, B., and Yazici, B. (2017, January 8\u201312). Deep learning for radar. Proceedings of the IEEE Radar Conference (RadarConf), Seattle, WA, USA.","DOI":"10.1109\/RADAR.2017.7944481"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"141800","DOI":"10.1109\/ACCESS.2021.3119561","article-title":"Deep-learning for radar: A survey","volume":"9","author":"Geng","year":"2021","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ross, T.D., Worrell, S.W., Velten, V.J., Mossing, J.C., and Bryant, M.L. (1998). Standard SAR ATR evaluation experiments using the MSTAR public release data set. SPIE Conference on Algorithms for Synthetic Aperture Radar Imagery V, International Society for Optics and Photonics.","DOI":"10.1117\/12.321859"},{"key":"ref_4","first-page":"1","article-title":"ATR of battlefield targets by SAR\u2014Classification results using the public MSTAR dataset compared with a dataset by QinetiQ, UK","volume":"Volume 31","author":"Schumacher","year":"2004","journal-title":"RTO Sensors and Electronics Technology Panel Symposium"},{"key":"ref_5","unstructured":"Schumacher, R., and Schiller, J. (2005, January 9\u201312). Non-cooperative target identification of battlefield targets-classification results based on SAR images. Proceedings of the IEEE International Radar Conference, Arlington, VA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MAES.2021.3049857","article-title":"Automatic target recognition on synthetic aperture radar imagery: A survey","volume":"36","author":"Aouf","year":"2021","journal-title":"IEEE Aerosp. Electron. Syst. Mag."},{"key":"ref_7","first-page":"39","article-title":"A SAR dataset for ATR development: The Synthetic and Measured Paired Labeled Experiment (SAMPLE)","volume":"10987","author":"Lewis","year":"2019","journal-title":"SPIE Conf. Algorithms Synth. Aperture Radar Imag. XXVI"},{"key":"ref_8","first-page":"29","article-title":"A deep learning approach to the Synthetic and Measured Paired and Labeled Experiment (SAMPLE) challenge problem","volume":"10987","author":"Scarnati","year":"2019","journal-title":"Algorithms Synth. Aperture Radar Imag. XXVI"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Arnold, J.M., Moore, L.J., and Zelnio, E.G. (2018, January 27). Blending synthetic and measured data using transfer learning for synthetic aperture radar (SAR) target classification. Proceedings of the SPIE conference on Algorithms for Synthetic Aperture Radar Imagery XXV, Orlando, FL, USA.","DOI":"10.1117\/12.2304568"},{"key":"ref_10","unstructured":"Friedlander, R.D., Levy, M., Sudkamp, E., and Zelnio, E.G. (2018, January 9). Deep learning model-based algorithm for SAR ATR. Proceedings of the SPIE conference on Algorithms for Synthetic Aperture Radar Imagery XXV, Orlando, FL, USA."},{"key":"ref_11","first-page":"53","article-title":"Review of recent advances in AI\/ML using the MSTAR data","volume":"11393","author":"Blasch","year":"2020","journal-title":"SPIE Conf. Algorithms Synth. Aperture Radar Imag. XXVII"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"27003","DOI":"10.1109\/ACCESS.2021.3057455","article-title":"SAR image generation of ground targets for automatic target recognition using indirect information","volume":"9","author":"Yoo","year":"2021","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sellers, S.R., Collins, P.J., and Jackson, J.A. (2020, January 28\u201330). Augmenting simulations for SAR ATR neural network training. Proceedings of the IEEE International Radar Conference (RADAR), Washington, DC, USA.","DOI":"10.1109\/RADAR42522.2020.9114867"},{"key":"ref_14","first-page":"364","article-title":"Convolutional neural network with data augmentation for SAR target recognition","volume":"13","author":"Ding","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2942","DOI":"10.1109\/JSTARS.2021.3059991","article-title":"Bridging a gap in SAR-ATR: Training on fully synthetic and testing on measured data","volume":"14","author":"Inkawhich","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_16","first-page":"109870C","article-title":"Realistic SAR data augmentation using machine learning techniques","volume":"10987","author":"Lewis","year":"2019","journal-title":"SPIE Conf. Algorithms Synth. Aperture Radar Imag. XXVI"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3954","DOI":"10.1109\/JSTARS.2021.3068944","article-title":"Training SAR-ATR models for reliable operation in open-world environments","volume":"14","author":"Inkawhich","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2174","DOI":"10.1109\/TGRS.2020.3003264","article-title":"FEC: A feature fusion framework for SAR Target recognition based on electromagnetic scattering features and deep CNN Features","volume":"59","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Agarwal, T., Sugavanam, N., and Ertin, E. (2020, January 21\u201325). Sparse signal models for data augmentation in deep learning ATR. Proceedings of the IEEE Radar Conference (RadarConf20), Florence, Italy.","DOI":"10.1109\/RadarConf2043947.2020.9266382"},{"key":"ref_20","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 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1109\/TAES.2018.2864809","article-title":"Fusing deep learning and sparse coding for SAR ATR","volume":"55","author":"Aouf","year":"2019","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_22","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_23","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MAES.2020.3000318","article-title":"Multirotors video synthetic aperture radar: System development and signal processing","volume":"35","author":"Zhang","year":"2020","journal-title":"IEEE Aerosp. Electron. Syst. Mag."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Malmgren-Hansen, D., and Nobel-J\u03d5rgensen, M. (2015, January 7\u201310). Convolutional neural networks for SAR image segmentation. Proceedings of the IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Abu Dhabi, United Arab Emirates.","DOI":"10.1109\/ISSPIT.2015.7394333"},{"key":"ref_25","unstructured":"Hendrycks, D., Mazeika, M., and Dietterich, T.G. (2019). Deep anomaly detection with outlier exposure. arXiv."},{"key":"ref_26","first-page":"242","article-title":"Civilian vehicle radar data domes","volume":"7699","author":"Dungan","year":"2010","journal-title":"Proc. SPIE"},{"key":"ref_27","unstructured":"Liang, S., Li, Y., and Srikant, R. (2018). Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv."},{"key":"ref_28","unstructured":"Lee, K., Lee, H., Lee, K., and Shin, J. (2018). Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Heiligers, M., and Huizing, A. (2018, January 23\u201327). On the importance of visual explanation and segmentation for SAR ATR using deep learning. Proceedings of the IEEE Radar Conference (RadarConf18), Oklahoma City, OK, USA.","DOI":"10.1109\/RADAR.2018.8378591"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2070","DOI":"10.1109\/JSTARS.2022.3146362","article-title":"Improving out-of-distribution detection by learning from the deployment environment","volume":"15","author":"Inkawhich","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/941\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:05:33Z","timestamp":1760119533000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/941"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,13]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23020941"],"URL":"https:\/\/doi.org\/10.3390\/s23020941","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,13]]}}}