{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:36:27Z","timestamp":1763202987673,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T00:00:00Z","timestamp":1755302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Synthetic aperture radar (SAR) image classification under limited data conditions faces two major challenges: inter-class similarity, where distinct radar targets (e.g., tanks and armored trucks) have nearly identical scattering characteristics, and intra-class variability, caused by speckle noise, pose changes, and differences in depression angle. To address these challenges, we propose MHD-ProtoNet, a meta-learning framework that extends prototypical networks with two key innovations: margin-aware hard example mining to better separate confusable classes by enforcing prototype distance margins, and dual-loss optimization to refine embeddings and improve robustness to noise-induced variations. Evaluated on the MSTAR dataset in a five-way one-shot task, MHD-ProtoNet achieves 76.80% accuracy, outperforming the Hybrid Inference Network (HIN) (74.70%), as well as standard few-shot methods such as prototypical networks (69.38%), ST-PN (72.54%), and graph-based models like ADMM-GCN (61.79%) and DGP-NET (68.60%). By explicitly mitigating inter-class ambiguity and intra-class noise, the proposed model enables robust SAR target recognition with minimal labeled data.<\/jats:p>","DOI":"10.3390\/a18080519","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T15:34:53Z","timestamp":1755531293000},"page":"519","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MHD-Protonet: Margin-Aware Hard Example Mining for SAR Few-Shot Learning via Dual-Loss Optimization"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7965-7584","authenticated-orcid":false,"given":"Marii","family":"Zayani","sequence":"first","affiliation":[{"name":"Smart Systems for Engineering and E-Health Based on Image and Telecommunication Technologies (SETIT Lab), Higher Institute of Biotechnology of Sfax (ISBS), University of Sfax, Sfax 3000, Tunisia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8415-0871","authenticated-orcid":false,"given":"Abdelmalek","family":"Toumi","sequence":"additional","affiliation":[{"name":"Research Laboratory in Information and Communication Science and Technology (Lab-STICC), UMR CNRS 6285, ENSTA, Institut Polytechnique de Paris, 29200 Brest, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2279-9111","authenticated-orcid":false,"given":"Ali","family":"Khalfallah","sequence":"additional","affiliation":[{"name":"Smart Systems for Engineering and E-Health Based on Image and Telecommunication Technologies (SETIT Lab), Higher Institute of Biotechnology of Sfax (ISBS), University of Sfax, Sfax 3000, Tunisia"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,16]]},"reference":[{"key":"ref_1","unstructured":"Zhang, R., Wang, Z., Li, Y., Wang, J., and Wang, Z. (2023). FewSAR: A Few-Shot SAR Image Classification Benchmark. arXiv, Available online: https:\/\/arxiv.org\/abs\/2306.09592."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e1264","DOI":"10.1002\/widm.1264","article-title":"Deep Learning for Remote Sensing Image Classification: A Survey","volume":"8","author":"Li","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, X., Sun, H., Zhang, Z., Diao, W., and Fu, K. (2018, January 22\u201327). High Resolution SAR Image Classification with Deeper Convolutional Neural Network. Proceedings of the IGARSS 2018\u20142018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8518829"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.1109\/TGRS.2017.2777868","article-title":"SAR Image Classification via Deep Recurrent Encoding Neural Networks","volume":"56","author":"Geng","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"El Housseini, A., Toumi, A., and Khenchaf, A. (2017, January 20\u201322). Deep Learning for Target Recognition from SAR Images. Proceedings of the 2017 Seminar on Detection Systems Architectures and Technologies (DAT), Algiers, Algeria.","DOI":"10.1109\/DAT.2017.7889171"},{"key":"ref_6","unstructured":"Toumi, A., Cexus, J.-C., Khenchaf, A., and Tartivel, A. (2020, January 12\u201316). Transfer Learning on CNN Architectures for Ship Classification on SAR Images. Proceedings of the Sea Tech Week\u2014Session Remote Sensing, Brest, France. Available online: https:\/\/hal.science\/hal-03109596."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Toumi, A., Cexus, J.-C., and Khenchaf, A. (2024, January 11\u201313). Comparative Performances of CNN Models for SAR Targets Classification. Proceedings of the 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP), Sousse, Tunisia.","DOI":"10.1109\/ATSIP62566.2024.10638905"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Toumi, A., Cexus, J.-C., Khenchaf, A., and Abid, M. (2024). A Combined CNN-LSTM Network for Ship Classification on SAR Images. Sensors, 24.","DOI":"10.3390\/s24247954"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kong, J., and Zhang, F. (2021, January 15\u201318). SAR Target Recognition with Generative Adversarial Network (GAN)-Based Data Augmentation. Proceedings of the 2021 13th International Conference on Advanced Infocomm Technology (ICAIT), Yanji, China.","DOI":"10.1109\/ICAIT52638.2021.9701974"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Tang, J., Zhang, F., Zhou, Y., Yin, Q., and Hu, W. (August, January 28). A Fast Inference Network for SAR Target Few-Shot Learning Based on Improved Siamese Networks. Proceedings of the IGARSS 2019\u20142019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8898180"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Khenchaf, Y., and Toumi, A. (2023, January 16\u201321). Siamese Neural Network for Automatic Target Recognition Using Synthetic Aperture Radar. Proceedings of the IGARSS 2023\u20142023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA.","DOI":"10.1109\/IGARSS52108.2023.10281529"},{"key":"ref_12","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. arXiv, Available online: https:\/\/arxiv.org\/abs\/1703.03400."},{"key":"ref_13","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017). Prototypical Networks for Few-Shot Learning. arXiv, Available online: https:\/\/arxiv.org\/abs\/1703.05175."},{"key":"ref_14","unstructured":"Li, Z., Yang, F., Song, F., Hou, L., Wang, K., and Yang, Y. (2017). Meta-SGD: Learning to Learn Stochastic Gradient Descent. arXiv, Available online: https:\/\/arxiv.org\/pdf\/1707.09835."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhao, P., Huang, L., Xin, Y., Guo, J., and Pan, Z. (2021). Multi-Aspect SAR Target Recognition Based on Prototypical Network with a Small Number of Training Samples. Sensors, 21.","DOI":"10.3390\/s21134333"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yu, X., Yu, H., Liu, Y., and Ren, H. (2024). Enhanced Prototypical Network with Customized Region-Aware Convolution for Few-Shot SAR ATR. Remote Sens., 16.","DOI":"10.20944\/preprints202407.2260.v1"},{"key":"ref_17","first-page":"1","article-title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","volume":"53","author":"Wang","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, N., Jin, W., Bi, H., Xu, C., and Gao, J. (2024). A Survey on Deep Learning for Few-Shot PolSAR Image Classification. Remote Sens., 16.","DOI":"10.3390\/rs16244632"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s13735-023-00279-4","article-title":"Few-Shot and Meta-Learning Methods for Image Understanding: A Survey","volume":"12","author":"He","year":"2023","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ref_20","first-page":"1","article-title":"Few-Shot SAR Target Classification via Meta-Learning","volume":"60","author":"Fu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","unstructured":"Ravi, S., and Larochelle, H. (2017, January 24\u201326). Optimization as a Model for Few-Shot Learning. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France. Available online: https:\/\/openreview.net\/pdf?id=rJY0-Kcll."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Demertzis, K., and Iliadis, L. (2020). GeoAI: A Model-Agnostic Meta-Ensemble Zero-Shot Learning Method for Hyperspectral Image Analysis and Classification. Algorithms, 13.","DOI":"10.3390\/a13030061"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, X., and Luo, Y. (2025). Feature Transformation-Based Few-Shot Class-Incremental Learning. Algorithms, 18.","DOI":"10.3390\/a18070422"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, A., Huang, W., Lan, X., Feng, J., Li, Z., and Wang, L. (2020). Boosting Few-Shot Learning with Adaptive Margin Loss. arXiv, Available online: https:\/\/arxiv.org\/abs\/2005.13826.","DOI":"10.1109\/CVPR42600.2020.01259"},{"key":"ref_25","unstructured":"Arik, S.O., and Pfister, T. (2019). ProtoAttend: Attention-Based Prototypical Learning. arXiv, Available online: https:\/\/arxiv.org\/abs\/1902.06292."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, T., Ke, Z., Li, Y., and Silamu, W. (2023). Knowledge-Enhanced Prototypical Network with Class Cluster Loss for Few-Shot Relation Classification. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0286915"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hamzaoui, M., Chapel, L., Pham, M.T., and Lef\u00e8vre, S. (2022, January 1\u20133). A Hierarchical Prototypical Network for Few-Shot Remote Sensing Scene Classification. Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence, Paris, France.","DOI":"10.1007\/978-3-031-09282-4_18"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cai, J., Zhang, Y., Guo, J., Zhao, X., Lv, J., and Hu, Y. (2022). ST-PN: A Spatial Transformed Prototypical Network for Few-Shot SAR Image Classification. Remote Sens., 14.","DOI":"10.3390\/rs14092019"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Patel, K., Bhatt, C., and Mazzeo, P.L. (2022). Improved Ship Detection Algorithm from Satellite Images Using YOLOv7 and Graph Neural Network. Algorithms, 15.","DOI":"10.3390\/a15120473"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jin, J., Xu, Z., Zheng, N., and Wang, F. (2025). Graph-Based Few-Shot Learning for Synthetic Aperture Radar Automatic Target Recognition with Alternating Direction Method of Multipliers. Remote Sens., 17.","DOI":"10.3390\/rs17071179"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Xu, C., Gao, L., Su, H., Zhang, J., Wu, J., and Yan, W. (2023). Label Smoothing Auxiliary Classifier Generative Adversarial Network with Triplet Loss for SAR Ship Classification. Remote Sens., 15.","DOI":"10.3390\/rs15164058"},{"key":"ref_32","unstructured":"Zhou, X., Wei, Q., and Zhang, Y. (2023). DGP-Net: Dense Graph Prototype Network for Few-Shot SAR Target Recognition. arXiv, Available online: https:\/\/arxiv.org\/abs\/2302.09584."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., and Philbin, J. (2015, January 7\u201312). FaceNet: A Unified Embedding for Face Recognition and Clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., and Girshick, R. (2016, January 27\u201330). Training Region-Based Object Detectors with Online Hard Example Mining. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Manmatha, R., Smola, A.J., and Krahenbuhl, P. (2017, January 22\u201329). Sampling Matters in Deep Embedding Learning. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref_37","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201318). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the International Conference on Machine Learning (ICML), Virtual. Available online: http:\/\/proceedings.mlr.press\/v119\/chen20a.html."},{"key":"ref_38","unstructured":"Wang, Y., Wu, X.M., Li, Q., Gu, J., Xiang, W., Zhang, L., and Li, V.O. (2018). Large Margin Few-Shot Learning. arXiv, Available online: https:\/\/arxiv.org\/abs\/1807.02872."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liu, B., Cao, Y., Lin, Y., Li, Q., Zhang, Z., Long, M., and Hu, H. (2020). Negative Margin Matters: Understanding Margin in Few-Shot Classification. arXiv, Available online: https:\/\/arxiv.org\/abs\/2003.12060.","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liao, L., Du, L., Zhang, W., and Chen, J. (2022). Adaptive Max-Margin One-Class Classifier for SAR Target Discrimination in Complex Scenes. Remote Sens., 14.","DOI":"10.3390\/rs14092078"},{"key":"ref_41","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_42","unstructured":"Hermans, A., Beyer, L., and Leibe, B. (2017). In Defense of the Triplet Loss for Person Re-Identification. arXiv, Available online: https:\/\/arxiv.org\/abs\/1703.07737."},{"key":"ref_43","unstructured":"Defense Advanced Research Project Agency (DARPA), and Air Force Research Laboratory (AFRL) (2025, May 24). The Air Force Moving and Stationary Target Recognition (MSTAR) Database. Available online: https:\/\/www.sdms.afrl.af.mil\/index.php?collection=mstar."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., and Hospedales, T.M. (2018, January 18\u201323). Learning to Compare: Relation Network for Few-Shot Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Lu, C., and Li, W. (2018). Ship Classification in High-Resolution SAR Images via Transfer Learning with Small Training Dataset. Sensors, 19.","DOI":"10.3390\/s19010063"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Huang, Z., Pan, Z., and Lei, B. (2017). Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data. Remote Sens., 9.","DOI":"10.3390\/rs9090907"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Singh, A., and Singh, V.K. (2023). Exploring Deep Learning Methods for Classification of SAR Images: Towards NextGen Convolutions via Transformers. arXiv, Available online: https:\/\/arxiv.org\/abs\/2303.15852.","DOI":"10.1007\/978-3-031-28183-9_18"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A Survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/8\/519\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:29:06Z","timestamp":1760034546000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/8\/519"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,16]]},"references-count":48,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["a18080519"],"URL":"https:\/\/doi.org\/10.3390\/a18080519","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,8,16]]}}}