An experimental comparison of the widely used pre-trained deep neural networks for image classification tasks towards revealing the promise of transfer-learning

Basit Öğe Kaydı
dc.authoridKabakuş, Abdullah Talha/0000-0003-2181-4292
dc.authorwosidKabakuş, Abdullah Talha/J-8361-2019
dc.contributor.authorKabakuş, Abdullah Talha
dc.contributor.authorErdogmus, Pakize
dc.date.accessioned2023-07-26T11:58:09Z
dc.date.available2023-07-26T11:58:09Z
dc.date.issued2022
dc.departmentDÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractThe easiest way to propose a solution based on deep neural networks is using the pre-trained models through the transfer-learning technique. Deep learning platforms provide various pre-trained deep neural networks that can be easily applied for image classification tasks. So, Which pre-trained model provides the best performance for image classification tasks? is a question that instinctively comes to mind and should be shed light on by the research community. To this end, we propose an experimental comparison of the six popular pre-trained deep neural networks, namely, (i) VGG19, (ii) ResNet50, (iii) DenseNet201, (iv) MobileNetV2, (v) InceptionV3, and (vi) Xception by employing them through the transfer-learning technique. Then, the proposed benchmark models were both trained and evaluated under the same configurations on two gold-standard datasets, namely, (i) CIFAR-10 and (ii) Stanford Dogs to benchmark them. Three evaluation metrics were employed to measure performance differences between the employed pre-trained models as follows: (i) Accuracy, (ii) training duration, and (iii) inference time. The key findings that were obtained through the conducted a wide variety of experiments were discussed.en_US
dc.identifier.doi10.1002/cpe.7216
dc.identifier.issn1532-0626
dc.identifier.issn1532-0634
dc.identifier.issue24en_US
dc.identifier.scopus2-s2.0-85134766477en_US
dc.identifier.scopusqualityQ3en_US
dc.identifier.urihttps://doi.org/10.1002/cpe.7216
dc.identifier.urihttps://hdl.handle.net/20.500.12684/13415
dc.identifier.volume34en_US
dc.identifier.wosWOS:000830194200001en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.institutionauthorKabakuş, Abdullah Talha
dc.institutionauthorErdoğmuş, Pakize
dc.language.isoenen_US
dc.publisherWileyen_US
dc.relation.ispartofConcurrency and Computation-Practice & Experienceen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz$2023V1Guncelleme$en_US
dc.subjectConvolutional Neural Network; Deep Learning; Deep Neural Network; Keras; Tensorflow; Transfer-Learningen_US
dc.titleAn experimental comparison of the widely used pre-trained deep neural networks for image classification tasks towards revealing the promise of transfer-learningen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
13415.pdf
Boyut:
2.03 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu