Targeted data augmentation for improving modelrobustness against systematic bias

Targeted data augmentation for improving modelrobustness against systematic bias | 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 Article Targeted data augmentation for improving modelrobustness against systematic bias Agnieszka Mikołajczyk-Bareła, Maria Ferlin, Michał Grochowski This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3953661/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The paper proposes a new and effective bias mitigation method called Targeted Data Augmentation (TDA). Since removingbiases is a tedious, always difficult and, on the other hand, not necessarily an effective approach the authors propose toskillfully insert them, instead. To show the efficiency and to validate the proposed approach, two representative and verydiverse datasets: the dataset of clinical skin lesions and the dataset of male and female faces, were selected to serve as thebenchmarks. The existing biases were first manually examined, identified, and annotated. Then, the use of CounterfactualBias Insertion, has provided the confirmation that the biases like the frame, ruler, and glasses, strongly affect the models. Tomake the models more robust against them, Targeted Data Augmentation was used: in short, the samples were modifiedduring training by randomly inserting biases. The proposed method resulted in a significant decrease in bias measures, morespecifically, from a two-fold to more than 50-fold improvement after training with TDA, with a negligible increase in the error rate. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-3953661","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":277835955,"identity":"012760de-c5fd-46e0-9e34-4ef1ec1d84a8","order_by":0,"name":"Agnieszka Mikołajczyk-Bareła","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABTklEQVRIie3RPWuDQBgH8DssZqjB9XGpX+EkEFKwyVdRhEzdCsWhhJPCZTF0NVDyDQqRgmRUhGQRslrI4pIpFLN1cOgptkNN6Fqofzi4t9+9ItSmzR9NyAspKxFFA4Qp4sWuRsrewW8EapJ8Ezi3U0UwrSdgh50n8tNLFObFpCfTSzPybFCF6WavzBe7Ie08BoBXDQLpuxHNmdiHsLuMlglojmuMFT/YW1Ra3wNOmgdLExJ3qaSjkmQMsOOhtZIFsYXgtg+YNYhakqIAXa3JyPEwU7JnTtTDSUK2LomRSPqkJD4D0/EEUfFpPEQgnSRaKpFoxoyeFnPiJWA57li49tZ7Q5TGdwOzeZerbdLLP4qJttjMXo+urd/400325j7sRnIn9tPjSm9cH4y6InztS9EFXzk0q68xaUMgOfz5IFznnIyqFj5B2rRp0+a/5RMQ5X01TJLT3AAAAABJRU5ErkJggg==","orcid":"","institution":"Gdańsk University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Agnieszka","middleName":"","lastName":"Mikołajczyk-Bareła","suffix":""},{"id":277835956,"identity":"ddfb8511-4687-431f-8ced-5a5319310344","order_by":1,"name":"Maria Ferlin","email":"","orcid":"","institution":"Gdańsk University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"","lastName":"Ferlin","suffix":""},{"id":277835957,"identity":"007dd6cf-ec18-4271-a968-6e6894bc994e","order_by":2,"name":"Michał Grochowski","email":"","orcid":"","institution":"Gdańsk University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Michał","middleName":"","lastName":"Grochowski","suffix":""}],"badges":[],"createdAt":"2024-02-13 14:00:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3953661/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3953661/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56638023,"identity":"3c3551ec-c31b-42c5-8db1-8503bb76a073","added_by":"auto","created_at":"2024-05-17 04:38:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":310392,"visible":true,"origin":"","legend":"","description":"","filename":"TargetedDataAugmentationScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3953661/v1_covered_ea555436-228e-4c17-91f3-167074e9c1dd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Targeted data augmentation for improving modelrobustness against systematic bias","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3953661/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3953661/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The paper proposes a new and effective bias mitigation method called Targeted Data Augmentation (TDA). Since removingbiases is a tedious, always difficult and, on the other hand, not necessarily an effective approach the authors propose toskillfully insert them, instead. To show the efficiency and to validate the proposed approach, two representative and verydiverse datasets: the dataset of clinical skin lesions and the dataset of male and female faces, were selected to serve as thebenchmarks. The existing biases were first manually examined, identified, and annotated. Then, the use of CounterfactualBias Insertion, has provided the confirmation that the biases like the frame, ruler, and glasses, strongly affect the models. Tomake the models more robust against them, Targeted Data Augmentation was used: in short, the samples were modifiedduring training by randomly inserting biases. The proposed method resulted in a significant decrease in bias measures, morespecifically, from a two-fold to more than 50-fold improvement after training with TDA, with a negligible increase in the error rate.","manuscriptTitle":"Targeted data augmentation for improving modelrobustness against systematic bias","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-11 19:54:35","doi":"10.21203/rs.3.rs-3953661/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1d21cdb1-42e1-4dcc-b004-aa04770fe36b","owner":[],"postedDate":"March 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":29270515,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":29270516,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-05-17T04:38:40+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-11 19:54:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3953661","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3953661","identity":"rs-3953661","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}