Full metadata record

DC Field Value Language
dc.contributor.authorIm, Seongil-
dc.contributor.authorJeong, Jae-Seung-
dc.contributor.authorLee, Junseo-
dc.contributor.authorShin, Changhwan-
dc.contributor.authorCho, Jeong Ho-
dc.contributor.authorJu, Hyunsu-
dc.date.accessioned2024-05-02T02:30:10Z-
dc.date.available2024-05-02T02:30:10Z-
dc.date.created2024-05-02-
dc.date.issued2024-04-
dc.identifier.issn0899-7667-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/149775-
dc.description.abstractRecent advancements in deep learning have achieved significant progress by increasing the number of parameters in a given model. However, this comes at the cost of computing resources, prompting researchers to explore model compression techniques that reduce the number of parameters while maintaining or even improving performance. Convolutional neural networks (CNN) have been recognized as more efficient and effective than fully connected (FC) networks. We propose a column row convolutional neural network (CRCNN) in this letter that applies 1D convolution to image data, significantly reducing the number of learning parameters and operational steps. The CRCNN uses column and row local receptive fields to perform data abstraction, concatenating each direction's feature before connecting it to an FC layer. Experimental results demonstrate that the CRCNN maintains comparable accuracy while reducing the number of parameters and compared to prior work. Moreover, the CRCNN is employed for one-class anomaly detection, demonstrating its feasibility for various applications.-
dc.languageEnglish-
dc.publisherMIT Press-
dc.titleColumn Row Convolutional Neural Network: Reducing Parameters for Efficient Image Processing-
dc.typeArticle-
dc.identifier.doi10.1162/neco_a_01653-
dc.description.journalClass1-
dc.identifier.bibliographicCitationNeural Computation, v.36, no.4, pp.744 - 758-
dc.citation.titleNeural Computation-
dc.citation.volume36-
dc.citation.number4-
dc.citation.startPage744-
dc.citation.endPage758-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.identifier.wosid001207798800001-
dc.identifier.scopusid2-s2.0-85189119767-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.relation.journalWebOfScienceCategoryNeurosciences-
dc.relation.journalResearchAreaComputer Science-
dc.relation.journalResearchAreaNeurosciences & Neurology-
dc.type.docTypeArticle-
Appears in Collections:
KIST Article > 2024
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE