GatherNet: The Lightest Convolutional Neural Network Architecture So far
preprint
OA: closed
AI-generated deep summary
This preprint studied how to design an extremely lightweight convolutional neural network for mobile-resource settings by proposing a new Gather module that combines depthwise separable convolution, standard convolution, and a Ghost module, with channel shuffle to enhance information flow across channels. Based on this module, the authors constructed GatherNet, and they added a hard-swish activation function to address data collapse when low-dimensional features are embedded into higher-dimensional spaces during training. Across CIFAR-10, ImageNet-1K, and VOC, GatherNet reportedly achieved competitive classification and detection performance with far fewer parameters than other lightweight models, and it performed best under a smaller training sample regime and in an ocular surface disease recognition application. The authors note this is a preprint that has not been peer reviewed. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.
Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works
Abstract
Abstract It is generally difficult to establish convolutional neural networks with many operations on mobile devices due to their limited memory and computation resources. This paper proposes a novel Gather module that combines depthwise separable convolution and standard convolution with Ghost module to generate feature maps cheaply and efficiently and uses channel shuffle to rearrange these learned feature maps to improve the information flow between different feature channels. Based on the Gather module, we construct a novel network architecture called GatherNet which is the lightest convolutional neural network architecture so far. We also introduce a hard-swish activation function to effectively solve the data collapse when low-dimensional features are embedded in a high-dimensional space during training. Three benchmark datasets of CIFAR-10, ImageNet-1K, and VOC are used to evaluate our network, with the validation results showing that our proposed GatherNet achieves competitive classification and detection results with much fewer weight parameters than state-of-the-art lightweight network models. Particularly, our GatherNet works much better on a small set of training samples than other lightweight models and still shows the best performance with much fewer parameters and better accuracy when applying it to ocular surface disease recognition. The pre-trained GatherNet model with its code is available at GitHub: https://github.com/Rchen3233/GatherNet.
Full text
10,365 characters
· extracted from
preprint-html
· click to expand
GatherNet: The Lightest Convolutional Neural Network Architecture So far | 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 GatherNet: The Lightest Convolutional Neural Network Architecture So far Wenkang Fan, Xiongbiao Luo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4580378/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 It is generally difficult to establish convolutional neural networks with many operations on mobile devices due to their limited memory and computation resources. This paper proposes a novel Gather module that combines depthwise separable convolution and standard convolution with Ghost module to generate feature maps cheaply and efficiently and uses channel shuffle to rearrange these learned feature maps to improve the information flow between different feature channels. Based on the Gather module, we construct a novel network architecture called GatherNet which is the lightest convolutional neural network architecture so far. We also introduce a hard-swish activation function to effectively solve the data collapse when low-dimensional features are embedded in a high-dimensional space during training. Three benchmark datasets of CIFAR-10, ImageNet-1K, and VOC are used to evaluate our network, with the validation results showing that our proposed GatherNet achieves competitive classification and detection results with much fewer weight parameters than state-of-the-art lightweight network models. Particularly, our GatherNet works much better on a small set of training samples than other lightweight models and still shows the best performance with much fewer parameters and better accuracy when applying it to ocular surface disease recognition. The pre-trained GatherNet model with its code is available at GitHub: https://github.com/Rchen3233/GatherNet . Lightweight Networks Convolutional Neural Networks Object Detection and Recognition Depthwise Separable Convolution ShuttleNet MobileNet GhostNet 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-4580378","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":317787450,"identity":"06714bae-bacf-4ceb-996d-8767381bff83","order_by":0,"name":"Wenkang Fan","email":"data:image/png;base64,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","orcid":"","institution":"Xiamen University","correspondingAuthor":true,"prefix":"","firstName":"Wenkang","middleName":"","lastName":"Fan","suffix":""},{"id":317787451,"identity":"77ff1366-b282-41dc-a0b5-61e66edc318a","order_by":1,"name":"Xiongbiao Luo","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Xiongbiao","middleName":"","lastName":"Luo","suffix":""}],"badges":[],"createdAt":"2024-06-14 07:48:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4580378/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4580378/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60938694,"identity":"bb435136-c51f-4d0d-bd86-f6c3235f36e1","added_by":"auto","created_at":"2024-07-23 20:09:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2338920,"visible":true,"origin":"","legend":"","description":"","filename":"kpaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4580378/v1_covered_d2a5b9da-5f3c-447b-8775-4467bbf83697.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GatherNet: The Lightest Convolutional Neural Network Architecture So far","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":"Lightweight Networks, Convolutional Neural Networks, Object Detection and Recognition, Depthwise Separable Convolution, ShuttleNet, MobileNet, GhostNet","lastPublishedDoi":"10.21203/rs.3.rs-4580378/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4580378/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"It is generally difficult to establish convolutional neural networks with many operations on mobile devices due to their limited memory and computation resources. This paper proposes a novel Gather module that combines depthwise separable convolution and standard convolution with Ghost module to generate feature maps cheaply and efficiently and uses channel shuffle to rearrange these learned feature maps to improve the information flow between different feature channels. Based on the Gather module, we construct a novel network architecture called GatherNet which is the lightest convolutional neural network architecture so far. We also introduce a hard-swish activation function to effectively solve the data collapse when low-dimensional features are embedded in a high-dimensional space during training. Three benchmark datasets of CIFAR-10, ImageNet-1K, and VOC are used to evaluate our network, with the validation results showing that our proposed GatherNet achieves competitive classification and detection results with much fewer weight parameters than state-of-the-art lightweight network models. Particularly, our GatherNet works much better on a small set of training samples than other lightweight models and still shows the best performance with much fewer parameters and better accuracy when applying it to ocular surface disease recognition. The pre-trained GatherNet model with its code is available at GitHub: https://github.com/Rchen3233/GatherNet.","manuscriptTitle":"GatherNet: The Lightest Convolutional Neural Network Architecture So far","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-03 16:39:20","doi":"10.21203/rs.3.rs-4580378/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":"16156eef-aee6-42d4-9f64-b1096f3b54e3","owner":[],"postedDate":"July 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-07-23T20:01:23+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-03 16:39:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4580378","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4580378","identity":"rs-4580378","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.
My notes (saved in your browser only)
Ask this paper
Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works
Citation neighborhood (no data yet)
We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2024) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.
Source provenance
- europepmc
- last seen: 2026-05-20T01:45:00.602351+00:00