WP-ViT2Level: Multi-Level Wavelet-Patch Vision Transformers for Robust SAR Automatic Target Recognition

WP-ViT2Level: Multi-Level Wavelet-Patch Vision Transformers for Robust SAR Automatic Target Recognition | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article WP-ViT2Level: Multi-Level Wavelet-Patch Vision Transformers for Robust SAR Automatic Target Recognition Aisha SIR ELKHATEM, Yerbol Ospanov, Madina Kamet, Aizhan Erulanova This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9186685/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract By integrating multi-level wavelet decomposition into the tokenization stage of Vision Transformers, we introduce a frequency-aware representation framework tailored for synthetic aperture radar (SAR) automatic target recognition (ATR). The proposed Wavelet-Patch Vision Transformer++ (WP-ViT++) decomposes SAR images into multi-resolution frequency sub-bands, enabling explicit separation of global structural information and high-frequency scattering features. Through wavelet-domain denoising and sub-band token embedding, the model enhances robustness against speckle noise while preserving discriminative target characteristics. A cross-wavelet attention mechanism further enables joint modeling of spatial–frequency dependencies, improving the representation of complex SAR signatures. Unlike conventional transformer-based approaches that rely solely on spatial patches, the proposed method incorporates domain-aligned frequency priors, leading to more stable and noise-resilient feature learning. Experimental results on the MSTAR benchmark demonstrate that WP-ViT + + achieves 93.6% classification accuracy, outperforming ViT, SpectFormer-Lite, and DiffFormer-Lite by significant margins. In addition, the proposed model maintains strong performance under noise perturbations, achieving over 93% accuracy under speckle noise conditions. These results confirm that wavelet-enhanced tokenization provides an effective and scalable solution for robust SAR ATR, improving both classification accuracy and generalization without increasing architectural complexity. SAR-ATR Multi-Scale Spectrum Pyramid Network Spatial-domain CNNs single-scale frequency-domain CNNs Feature Interpretability High-Frequency Scattering Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 03 May, 2026 Reviews received at journal 26 Apr, 2026 Reviewers agreed at journal 30 Mar, 2026 Reviewers invited by journal 29 Mar, 2026 Editor assigned by journal 23 Mar, 2026 Submission checks completed at journal 23 Mar, 2026 First submitted to journal 21 Mar, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9186685","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":614979290,"identity":"e775d55b-a338-4268-9d3a-f1f39148328d","order_by":0,"name":"Aisha SIR ELKHATEM","email":"","orcid":"","institution":"Sudan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Aisha","middleName":"SIR","lastName":"ELKHATEM","suffix":""},{"id":614979293,"identity":"dd9725e4-668f-43c3-bd88-50f98346b89e","order_by":1,"name":"Yerbol Ospanov","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABC0lEQVRIiWNgGAWjYHACNgaGAgSvvp+9gYEhoQCncqgWAwSPcWbPAaAWA5zKsWjZcCOBAUUEHRgc73324IMBg5z87OZnDz62MTBLznyd+OGBAUO+wQEcWs4cNzecYcBgbHDnmLnhzDYGNn7p3M0SQIdZbsCl5UYamzSPAUPiBokEM2meMww8krNzN4C0GOC05f4ziJb5M9K/gbRIGNw8u/kHXi032CBaGm7kAG2pAKq8wbsNry2SZ9LYgX6RAPrlTJnkjAqJBMme3G0WCQYSBpI4tPAdP8b24EOFDTDE2rdJfDCwSeBnP7v55o8KGwM+HFoUIOISYMQAI5EZGEC+gbCaUTAKRsEoGOkAAIknVXq/6jJgAAAAAElFTkSuQmCC","orcid":"","institution":"Seifullin Kazakh Agrotechnical Research University","correspondingAuthor":true,"prefix":"","firstName":"Yerbol","middleName":"","lastName":"Ospanov","suffix":""},{"id":614979294,"identity":"08aee85c-a252-4053-94aa-5787642655de","order_by":2,"name":"Madina Kamet","email":"","orcid":"","institution":"Shakarim State University Of Semey","correspondingAuthor":false,"prefix":"","firstName":"Madina","middleName":"","lastName":"Kamet","suffix":""},{"id":614979295,"identity":"fd1c85d9-c44f-4442-813b-bd0bc13a0d44","order_by":3,"name":"Aizhan Erulanova","email":"","orcid":"","institution":"Seifullin Kazakh Agrotechnical Research University","correspondingAuthor":false,"prefix":"","firstName":"Aizhan","middleName":"","lastName":"Erulanova","suffix":""}],"badges":[],"createdAt":"2026-03-21 15:10:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9186685/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9186685/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106094460,"identity":"50fde6cc-7816-474c-ae80-167367c2e71f","added_by":"auto","created_at":"2026-04-03 11:42:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":610746,"visible":true,"origin":"","legend":"","description":"","filename":"WaveletPatchVisionTransformersforRobustSARAutomaticTargetRecognition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9186685/v1_covered_b2a429f6-5b3f-414d-9bc1-0f35ba5acea4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"WP-ViT2Level: Multi-Level Wavelet-Patch Vision Transformers for Robust SAR Automatic Target Recognition","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"SAR-ATR, Multi-Scale Spectrum Pyramid Network, Spatial-domain CNNs, single-scale frequency-domain CNNs, Feature Interpretability, High-Frequency Scattering","lastPublishedDoi":"10.21203/rs.3.rs-9186685/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9186685/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBy integrating multi-level wavelet decomposition into the tokenization stage of Vision Transformers, we introduce a frequency-aware representation framework tailored for synthetic aperture radar (SAR) automatic target recognition (ATR). The proposed Wavelet-Patch Vision Transformer++ (WP-ViT++) decomposes SAR images into multi-resolution frequency sub-bands, enabling explicit separation of global structural information and high-frequency scattering features. Through wavelet-domain denoising and sub-band token embedding, the model enhances robustness against speckle noise while preserving discriminative target characteristics. A cross-wavelet attention mechanism further enables joint modeling of spatial\u0026ndash;frequency dependencies, improving the representation of complex SAR signatures. Unlike conventional transformer-based approaches that rely solely on spatial patches, the proposed method incorporates domain-aligned frequency priors, leading to more stable and noise-resilient feature learning. Experimental results on the MSTAR benchmark demonstrate that WP-ViT\u0026thinsp;+\u0026thinsp;+\u0026thinsp;achieves 93.6% classification accuracy, outperforming ViT, SpectFormer-Lite, and DiffFormer-Lite by significant margins. In addition, the proposed model maintains strong performance under noise perturbations, achieving over 93% accuracy under speckle noise conditions. These results confirm that wavelet-enhanced tokenization provides an effective and scalable solution for robust SAR ATR, improving both classification accuracy and generalization without increasing architectural complexity.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e","manuscriptTitle":"WP-ViT2Level: Multi-Level Wavelet-Patch Vision Transformers for Robust SAR Automatic Target Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-02 20:17:09","doi":"10.21203/rs.3.rs-9186685/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-03T22:28:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-26T07:04:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"10399743570162577978766356782945006454","date":"2026-03-30T07:48:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-29T04:35:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-24T01:05:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-24T01:05:06+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2026-03-21T15:00:57+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a3197684-7d72-4acd-8488-eee385d24c6d","owner":[],"postedDate":"April 2nd, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-03T22:28:02+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T15:09:23+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-02 20:17:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9186685","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9186685","identity":"rs-9186685","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}