Adaptive Multi-Scale Feature Fusion with Spatial Translation for semantic Segmentation

Adaptive Multi-Scale Feature Fusion with Spatial Translation for semantic Segmentation | 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 Adaptive Multi-Scale Feature Fusion with Spatial Translation for semantic Segmentation Hongru Wang, Haoyu Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4236445/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Aug, 2024 Read the published version in Signal, Image and Video Processing → Version 1 posted 7 You are reading this latest preprint version Abstract In image segmentation tasks,the extraction of multi-scale features enables models to better adapt to targets of diverse scales and capture semantic information more comprehensively. Additionally, the rational utilization of receptive fields assists models in better comprehending both local and global image structures.In this work, we combine the advantages of these two approaches and propose a novel adaptive module termed the MFFM. Module similar to the human eye’s visual system adaptively adjusts the focus and perceptual range to maximize the capture of target features. However, fixed-size convolutional kernels may result in information loss or confusion, leading to inaccuracies in segmentation outcomes, especially when dealing with highly similar images. To address this issue,we introduce spatial shift mechanism to perform pixel-level translation of the feature map,and by taking into account the relative relationship between pixels, the network can learn more discriminative features, thereby enhancing segmentation accuracy. Based on this, we propose a network model called AMFFNet. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and ADE20K datasets, achieving the test set performance of 91.7% and 46.76% MIoU without any post-processing. adaptive module MFFM spatial shift mechanism Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 Aug, 2024 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 25 May, 2024 Reviews received at journal 23 May, 2024 Reviewers agreed at journal 22 May, 2024 Reviewers invited by journal 10 Apr, 2024 Submission checks completed at journal 09 Apr, 2024 Editor assigned by journal 09 Apr, 2024 First submitted to journal 08 Apr, 2024 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-4236445","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":289938330,"identity":"a4243150-7e20-4eed-8ce5-ce4899e70d4e","order_by":0,"name":"Hongru Wang","email":"","orcid":"","institution":"Harbin Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Hongru","middleName":"","lastName":"Wang","suffix":""},{"id":289938331,"identity":"7a98414d-0042-4e30-a34f-fded67c07f18","order_by":1,"name":"Haoyu Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAz0lEQVRIiWNgGAWjYDACCSCuKLBJADMYGJiJ1HLGII10LYdJ0GJwu8eA4YDB+Tzz2c3HJBgqrBMb2M8ewK/lzhmQltvFMneOpUkwnElPbODJS8CrxexGjgHzB4PbiTMkcswkGNsOJzZI8BgQ1AK05RxQS/43CcZ/xGs5ALKFTYKxgQgt9jfSCoBakhNnyBwztkg4lm7cxpODX4vkjOQNDAcq7BJnSDc/vPGhxlq2n/0Mfi0MDBzmP+DsBCBmI6AeCNgfEFYzCkbBKBgFIxsAAGeRReOgV9bzAAAAAElFTkSuQmCC","orcid":"","institution":"Harbin Engineering University","correspondingAuthor":true,"prefix":"","firstName":"Haoyu","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-04-08 12:32:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4236445/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4236445/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-024-03477-7","type":"published","date":"2024-08-08T15:57:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":62298444,"identity":"21f0864e-b680-4622-8b3e-f9e21ed0f885","added_by":"auto","created_at":"2024-08-12 16:13:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1431339,"visible":true,"origin":"","legend":"","description":"","filename":"AFMMNet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4236445/v1_covered_2c6e612a-4e51-4b76-bc6a-91ab04d30019.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Multi-Scale Feature Fusion with Spatial Translation for semantic Segmentation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"adaptive module MFFM, spatial shift mechanism","lastPublishedDoi":"10.21203/rs.3.rs-4236445/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4236445/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn image segmentation tasks,the extraction of multi-scale features enables models to better adapt to targets of diverse scales and capture semantic information more comprehensively. Additionally, the rational utilization of receptive fields assists models in better comprehending both local and global image structures.In this work, we combine the advantages of these two approaches and propose a novel adaptive module termed the MFFM. Module similar to the human eye’s visual system adaptively adjusts the focus and perceptual range to maximize the capture of target features. However, fixed-size convolutional kernels may result in information loss or confusion, leading to inaccuracies in segmentation outcomes, especially when dealing with highly similar images. To address this issue,we introduce spatial shift mechanism to perform pixel-level translation of the feature map,and by taking into account the relative relationship between pixels, the network can learn more discriminative features, thereby enhancing segmentation accuracy. Based on this, we propose a network model called AMFFNet. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and ADE20K datasets, achieving the test set performance of 91.7% and 46.76% MIoU without any post-processing.\u003c/p\u003e","manuscriptTitle":"Adaptive Multi-Scale Feature Fusion with Spatial Translation for semantic Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-12 18:32:56","doi":"10.21203/rs.3.rs-4236445/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-05-25T13:24:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-23T04:42:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"125949144952560536481783304664103969797","date":"2024-05-23T03:08:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-10T23:53:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-09T07:25:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-09T07:25:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-04-08T12:31:27+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":"75c60cd0-5db1-408d-9338-2b3a824fbd38","owner":[],"postedDate":"April 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-08-12T16:04:02+00:00","versionOfRecord":{"articleIdentity":"rs-4236445","link":"https://doi.org/10.1007/s11760-024-03477-7","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2024-08-08 15:57:46","publishedOnDateReadable":"August 8th, 2024"},"versionCreatedAt":"2024-04-12 18:32:56","video":"","vorDoi":"10.1007/s11760-024-03477-7","vorDoiUrl":"https://doi.org/10.1007/s11760-024-03477-7","workflowStages":[]},"version":"v1","identity":"rs-4236445","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4236445","identity":"rs-4236445","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}