A new local pooling approach for convolutional neural network: local binary pattern

Basit Öğe Kaydı
dc.authoridDogan, Yahya/0000-0003-1529-6118
dc.authoridOZDEMIR, Cuneyt/0000-0002-9252-5888
dc.contributor.authorOzdemir, Cuneyt
dc.contributor.authorDogan, Yahya
dc.contributor.authorKaya, Yilmaz
dc.date.accessioned2024-12-24T19:24:42Z
dc.date.available2024-12-24T19:24:42Z
dc.date.issued2023
dc.departmentSiirt Üniversitesi
dc.description.abstractThe pooling layer used in CNN models aims to reduce the resolution of image/feature maps while retaining their distinctive information, reducing computation time and enabling deeper models. Max and average pooling methods are frequently used in CNN models due to their computational efficiency; however, these methods discard the position information of the pixels. In this study, we proposed an LBP-based pooling method that generates a neighborhood-based output for any pixel, reflecting the correlation between pixels in the local area. Our proposed method reduces information loss since it considers the neighborhood and size of the pixels in the pooling region. Experimental studies were performed on four public datasets to assess the effectiveness of the LBP pooling method. In experimental studies, a toy CNN model and various transfer learning models were utilized in conducting test operations. The proposed method provided improvements of 1.56% for Fashion MNIST, 0.22% for MNIST, 3.95% for CIFAR10, and 5% for CIFAR100 dataset using the toy model. In the experimental studies conducted using the transfer learning model, performance improvements of 6.99(-/+)(0.74) and 8.3(-/+)(0.1) were achieved for CIFAR10 and CIFAR100, respectively. We observed that the proposed method outperforms the commonly used pooling layers in CNN models. Code for this paper can be publicly accessed at: https://github.com/cuneytozdemir/lbppooling
dc.identifier.doi10.1007/s11042-023-17540-x
dc.identifier.issn1380-7501
dc.identifier.issn1573-7721
dc.identifier.scopus2-s2.0-85176250280
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1007/s11042-023-17540-x
dc.identifier.urihttps://hdl.handle.net/20.500.12604/6107
dc.identifier.wosWOS:001101620700002
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofMultimedia Tools and Applications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241222
dc.subjectPooling methods
dc.subjectConvolutional neural network
dc.subjectLocal binary pattern
dc.titleA new local pooling approach for convolutional neural network: local binary pattern
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu