[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-463000-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-463000-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","advancing-sar-target-recognition-through-hierarchical-self-supervised-learning-with-multi-task-pretext-training","Advancing SAR Target Recognition Through Hierarchical Self-Supervised Learning with Multi-Task Pretext Training","","Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems struggle with limited labeled data and ongoing domain gaps between synthetic and measured imagery. The work proposes a comprehensive self-supervised learning framework that removes reliance on synthetic data while reaching state-of-the-art results via multi-task pretext training and extensive evaluation. Experiments on the SAMPLE dataset compare multiple downstream classifiers across different model families, including classical methods, CNNs, and a generative adversarial network.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/advancing-sar-target-recognition-through-hierarchical-self-supervised-learning-with-multi-task-pretext-training/463000/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/advancing-sar-target-recognition-through-hierarchical-self-supervised-learning-with-multi-task-pretext-training/463000.png","ImageObject",300,407,{"name":42,"@type":43},"Well Done","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why do SAR ATR systems face difficulties compared with conventional computer vision tasks?","Question",{"text":63,"@type":64},"SAR imagery is shaped by electromagnetic scattering rather than literal visual appearance, making human interpretation and standard computer vision approaches less effective.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What main problems does the paper target in training SAR ATR models?",{"text":68,"@type":64},"It addresses limited availability of labeled data and persistent domain gaps between synthetic and measured SAR imagery.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the proposed framework improve SAR ATR performance?",{"text":72,"@type":64},"It uses a hierarchical self-supervised learning approach with multi-task pretext training, then evaluates the learned representations across many downstream classifier types using the SAMPLE dataset.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},463000,1790835597,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":97,"preview_urls":147},5909892210082,"https://ap-avatar.wpscdn.com/avatar/56001069da27c9f41e8?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789614185077863061","sensors   \nArticle  \nAdvancing SAR Target Recognition Through Hierarchical Self-Supervised Learning with Multi-Task Pretext Training Md Al Siam, Dewan Fahim Noor *, Mandoye Ndoye and Jesmin Farzana Khan  \nAcademic Editor: Antonio Iodice  \nReceived: 28 October 2025  \nRevised: 9 December 2025  \nAccepted: 16 December 2025  \nPublished: 24 December 2025  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \nElectrical & Computer Engineering Department, Tuskegee University, Tuskegee, AL 36088, USA;  \n[msiam0229@tuskegee.edu](msiam0229@tuskegee.edu) (M.A.S.); [mndoye@tuskegee.edu](mndoye@tuskegee.edu) (M.N.); [jkhan2@tuskegee.edu](jkhan2@tuskegee.edu) (J.F.K.)  \n* Correspondence: [dnoor@tuskegee.edu](dnoor@tuskegee.edu)  \nAbstract  \nSynthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems face significant challenges due to limited labeled data availability and persistent domain gaps between synthetic and measured imagery. This paper presents a comprehensive selfsupervised learning (SSL) framework that eliminates dependency on synthetic data while achieving state-of-the-art performance through multi-task pretext training and extensive downstream classifier evaluation. We systematically evaluate our SSL framework across diverse downstream classifiers spanning different computational paradigms and architectural families. Our study encompasses traditional machine learning approaches (SVM, Random Forest, XGBoost, Gradient Boosting), deep convolutional neural networks (ResNet, U-Net, MobileNet, EfficientNet), and a generative adversarial network. We conduct extensive experiments using the SAMPLE dataset with rigorous evaluation protocols. Results demonstrate that SSL significantly improves SAR ATR performance, with SVM achieving 99.63% accuracy, ResNet18 reaching 97.40% accuracy, and Random Forest demonstrating 99.26% accuracy. Our multi-task SSL framework employs nine carefully designed pretext tasks, including geometric invariance, signal robustness, and multi-scale analysis. Cross-validation experiments validate the generalizability and robustness of our findings. Rigorous comparison with SimCLR baseline validates that task-based SSL outperforms contrastive learning for SAR ATR. This work establishes a new paradigm for SAR ATR that leverages inherent radar data structure without synthetic augmentation, providing practical guidelines for deploying SSL-based SAR ATR systems and a foundation for future domain-specific self-supervised learning research in remote sensing applications.  \nKeywords: machine learning; deep learning; self-supervised learning (SSL); remote sensing; computer vision; signal processing; synthetic aperture radar (SAR); automatic target recognition (ATR)  \n1. Introduction  \nSynthetic Aperture Radar (SAR) systems have become indispensable tools for military surveillance, reconnaissance, and civilian monitoring applications because of their unique capability to provide high-resolution imagery regardless of weather conditions, cloud cover, or illumination. Unlike electro-optical (EO) sensors, SAR systems actively transmit electromagnetic signals and measure the backscattered energy, enabling consistent performance under diverse environmental conditions [1–3] . This all-weather capability makes SAR particularly valuable for modern defense systems and enables the rapid identification and classification of targets in complex operational environments [4,5] .  \nThe development of Automatic Target Recognition (ATR) systems for SAR imagery presents unique challenges that distinguish them from conventional computer vision tasks. SAR images exhibit “non-literal” characteristics where electromagnetic scattering properties dominate visual appearance, making human interpretation and traditional computer vision approaches less effective. The radar backscatter depends ","cbCaieuWKrDzkbkW","https://ap.wps.com/l/cbCaieuWKrDzkbkW","pdf",2954079,44,"English","# Introduction\n## Synthetic Aperture Radar and ATR Context\n## Challenges in SAR ATR\n## Operating Condition Space and Data Scarcity\n## Synthetic Data Generation and Domain Gaps\n## Motivation from the SAMPLE Dataset\n# Method and Experiments\n## Self-Supervised Learning Framework\n## Multi-Task Pretext Tasks\n## Downstream Classifier Evaluation\n## Baseline Comparison and Results","[{\"question\":\"Why do SAR ATR systems face difficulties compared with conventional computer vision tasks?\",\"answer\":\"SAR imagery is shaped by electromagnetic scattering rather than literal visual appearance, making human interpretation and standard computer vision approaches less effective.\"},{\"question\":\"What main problems does the paper target in training SAR ATR models?\",\"answer\":\"It addresses limited availability of labeled data and persistent domain gaps between synthetic and measured SAR imagery.\"},{\"question\":\"How does the proposed framework improve SAR ATR performance?\",\"answer\":\"It uses a hierarchical self-supervised learning approach with multi-task pretext training, then evaluates the learned representations across many downstream classifier types using the SAMPLE dataset.\"}]","Advancing SAR Target Recognition Through Hierarchical Self-Supervised Learning with Multi-Task Pretext Training | PDF",1790765919,111,[148,152,156,160,164],{"page_no":22,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/a7972b54722e1318b83e8e983e46f030.webp",983,1390,{"page_no":26,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/62d79297410c70e8bf342336c033641e.webp",982,1388,{"page_no":30,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/d0c96e281ec0b4ee151d49d3b11d8fff.webp",981,1387,{"page_no":33,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/c05c6a802108bfc60bd5cb8a30c9539b.webp",980,1385,{"page_no":97,"url":165,"width":166,"height":167},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/8674fa19ba3dcb87a063db2dbf8849d2.webp",979,1384]