{"paper_id":"2ce5782e-8946-4e5b-9cbe-63f58ca75632","body_text":"Contrastive Distillation Learning with Sparse Spatial Aggregation | 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Article Contrastive Distillation Learning with Sparse Spatial Aggregation Dan Cheng, Jun Yin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5364334/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 Contrastive learning has advanced significantly and demonstrates excellent transfer learning capabilities. Knowledge distillation is one of the most effective methods of model compression for computer vision. When combined with contrastive learning, it can achieve even better results. Current knowledge distillation techniques based on contrastive learning struggle to efficiently utilize the information from both student and teacher models, often missing out on optimizing the contrastive framework. This results in a less effective knowledge transfer process, limiting the potential improvements in model performance and representation quality. To address this limitation, we propose a new contrastive distillation learning method by redesigning the contrastive learning framework and incorporating sparse spatial aggregation. This method introduces a novel integration of feature alignment and spatial aggregation mechanism to enhance the learning process. It ensures that the representations obtained by the model fully capture the semantics of the original input. Compared to traditional unsupervised learning methods, our approach demonstrates superior performance in both pre-training and transfer learning. It achieves 71.6 Acc@1, 57.6 AP, 75.8 mIoU, 39.8/34.8 AP on ImageNet linear classification, Pascal VOC object detection, Cityscapes semantic segmentation, MS-COCO object detection and instance segmentation. Moreover, our method exhibits stable training and does not require large pre-training batch-sizes or numerous epochs. Contrastive learning Knowledge distillation Computer vision 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-5364334\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":372943421,\"identity\":\"3d058842-c726-4465-ba74-c8835662ef11\",\"order_by\":0,\"name\":\"Dan Cheng\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Shanghai Maritime University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Dan\",\"middleName\":\"\",\"lastName\":\"Cheng\",\"suffix\":\"\"},{\"id\":372943422,\"identity\":\"ca99f720-908d-4a25-95b6-e07f04522e2e\",\"order_by\":1,\"name\":\"Jun Yin\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYBACxgYgkcBgw2AA4TMTrSUNqIWZSC1QcJgELcwzco9JPNxx3t5c7PwxCYYK68QG9rMH8DtsRl6aROKZ24k7ZyezSTCcSU9s4MlLIKAlx0wise12gsFtoBbGtsOJDRI8BsRoOWcP0fKPeC0HGDeAtTQQo6XnjbFFYltyIlCLsUXCsXTjNp4c/FoM23MMb/5sswM6LPHhjQ811rL97GcIaGlgYJGA8xKAmA2veiCQB0bNB0KKRsEoGAWjYIQDABn/QrHTjBMnAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"Shanghai Maritime University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Jun\",\"middleName\":\"\",\"lastName\":\"Yin\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2024-10-31 02:53:11\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-5364334/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-5364334/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":72668106,\"identity\":\"b086362e-8c94-43f8-a1ee-06309409b2ee\",\"added_by\":\"auto\",\"created_at\":\"2024-12-31 04:01:33\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":311916,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"submission.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-5364334/v1_covered_c6aded81-8a6e-44d1-b1ca-63140e7e049a.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Contrastive Distillation Learning with Sparse Spatial Aggregation\",\"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\":\"info@researchsquare.com\",\"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\":\"Contrastive learning, Knowledge distillation, Computer vision\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-5364334/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-5364334/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eContrastive learning has advanced significantly and demonstrates excellent transfer learning capabilities. Knowledge distillation is one of the most effective methods of model compression for computer vision. When combined with contrastive learning, it can achieve even better results. Current knowledge distillation techniques based on contrastive learning struggle to efficiently utilize the information from both student and teacher models, often missing out on optimizing the contrastive framework. This results in a less effective knowledge transfer process, limiting the potential improvements in model performance and representation quality. To address this limitation, we propose a new contrastive distillation learning method by redesigning the contrastive learning framework and incorporating sparse spatial aggregation. This method introduces a novel integration of feature alignment and spatial aggregation mechanism to enhance the learning process. It ensures that the representations obtained by the model fully capture the semantics of the original input. Compared to traditional unsupervised learning methods, our approach demonstrates superior performance in both pre-training and transfer learning. It achieves 71.6 Acc@1, 57.6 AP, 75.8 mIoU, 39.8/34.8 AP on ImageNet linear classification, Pascal VOC object detection, Cityscapes semantic segmentation, MS-COCO object detection and instance segmentation. Moreover, our method exhibits stable training and does not require large pre-training batch-sizes or numerous epochs.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Contrastive Distillation Learning with Sparse Spatial Aggregation\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2024-11-13 04:34:22\",\"doi\":\"10.21203/rs.3.rs-5364334/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"78cb5e3f-32d4-4d8d-a350-3f654dcd20e5\",\"owner\":[],\"postedDate\":\"November 13th, 2024\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2024-12-31T03:53:24+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2024-11-13 04:34:22\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-5364334\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-5364334\",\"identity\":\"rs-5364334\",\"version\":[\"v1\"]},\"buildId\":\"qtupq5eGEP_6zYnWcrvyt\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}