Enhancing the classification accuracy by intra-concentration and the distance between the class boundaries instead of the class centers

Enhancing the classification accuracy by intra-concentration and the distance between the class boundaries instead of the class centers | 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 Enhancing the classification accuracy by intra-concentration and the distance between the class boundaries instead of the class centers Bahman Jafari Tabaghsar, Yahya Forghani, Reza Sheibani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4115663/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 softmax loss function is a commonly used loss function in the field of classification, which aims to increase the angle between two classes in feature space. However, it has some limitations such as class overlap and treating all misclassifications equally, and issue with imbalanced classes. Recently, the I2CS (Intra concentration and inter-separability) loss function has been proposed with a different approach from the softmax loss function, which is compressing data at the center and increasing class distance through the class center, which makes it able to overcome some of the limitations such as class-imbalanced problems, outliers and discover samples of unseen classes. Nevertheless, it still suffers from class overlap problem. Therefore, we have designed a new loss function with a novel approach to not only overcome the limitations of the softmax loss function but also address the class overlap issue of I2CS, and be effective in dealing with class imbalances. Furthermore, our purpose loss function has been thoroughly tested on a variety of standard benchmark datasets such as MNIST, CIFAR, and LFW as well as on imbalanced MNIST class, showcasing enhanced performance when contrasted with the softmax loss function and other widely-used loss functions. Deep learning Loss function Distance between the class boundaries inter-concentration Softmax loss 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-4115663","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":281003877,"identity":"efa0dbc5-1600-4ce3-9fb0-39a14dfd026d","order_by":0,"name":"Bahman Jafari Tabaghsar","email":"","orcid":"","institution":"Islamic Azad University, Mashhad","correspondingAuthor":false,"prefix":"","firstName":"Bahman","middleName":"Jafari","lastName":"Tabaghsar","suffix":""},{"id":281003878,"identity":"d9b6ba0b-0f4b-4831-b3b9-b098a494a184","order_by":1,"name":"Yahya Forghani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYBACgwM8QNKGgYGfmbHhwAcGhgQitaQxMEi2Nx98OIMYLZINUC0GZ44lG/MQo4Wf/ewxiR8JNvkMN3LMpG3b7PL42RsYP3zMwa2FjScvTbInIc2ycQZQS25bcrFkzwFmyZnb8GhhyDGT4P1x2IBZAqyFOXHDjQQ2Zl58WvjfmEn+SThswAbSYtlWT4QWkEoeoBYeHqD3GdsOE6PljbG1TEKagQQ7MJB7zh1PnNlzsBm/X/hzDG++SbAxsD8MjMofZdWJ/UC9Hz7i0QIELBJwJiMbmGzAqx4ImD8g2H8IKR4Fo2AUjIKRCAC8MVHZbYGQuQAAAABJRU5ErkJggg==","orcid":"","institution":"Islamic Azad University, Mashhad","correspondingAuthor":true,"prefix":"","firstName":"Yahya","middleName":"","lastName":"Forghani","suffix":""},{"id":281003879,"identity":"e9c3f841-ef74-4594-a78a-2525c79c774f","order_by":2,"name":"Reza Sheibani","email":"","orcid":"","institution":"Islamic Azad University, Mashhad","correspondingAuthor":false,"prefix":"","firstName":"Reza","middleName":"","lastName":"Sheibani","suffix":""}],"badges":[],"createdAt":"2024-03-17 06:29:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4115663/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4115663/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54129680,"identity":"3e189453-fdc7-4c26-a6b7-baeca2dbea4d","added_by":"auto","created_at":"2024-04-05 03:59:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":581275,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4115663/v1_covered_43ce1de3-2bea-4790-803e-d9d68e6787d9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing the classification accuracy by intra-concentration and the distance between the class boundaries instead of the class centers","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":"Deep learning, Loss function, Distance between the class boundaries, inter-concentration, Softmax loss","lastPublishedDoi":"10.21203/rs.3.rs-4115663/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4115663/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe softmax loss function is a commonly used loss function in the field of classification, which aims to increase the angle between two classes in feature space. However, it has some limitations such as class overlap and treating all misclassifications equally, and issue with imbalanced classes. Recently, the I2CS (Intra concentration and inter-separability) loss function has been proposed with a different approach from the softmax loss function, which is compressing data at the center and increasing class distance through the class center, which makes it able to overcome some of the limitations such as class-imbalanced problems, outliers and discover samples of unseen classes. Nevertheless, it still suffers from class overlap problem. Therefore, we have designed a new loss function with a novel approach to not only overcome the limitations of the softmax loss function but also address the class overlap issue of I2CS, and be effective in dealing with class imbalances. Furthermore, our purpose loss function has been thoroughly tested on a variety of standard benchmark datasets such as MNIST, CIFAR, and LFW as well as on imbalanced MNIST class, showcasing enhanced performance when contrasted with the softmax loss function and other widely-used loss functions.\u003c/p\u003e","manuscriptTitle":"Enhancing the classification accuracy by intra-concentration and the distance between the class boundaries instead of the class centers","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-20 06:51:45","doi":"10.21203/rs.3.rs-4115663/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":"f5b8ae9d-0b81-445e-a6f1-2ee84b44ea7e","owner":[],"postedDate":"March 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-05T03:59:25+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-20 06:51:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4115663","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4115663","identity":"rs-4115663","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}