Derin Öǧrenme Modelleri ile Eskiz Siniflandirma

Fevziye Irem Eyiokur; Dogucan Yaman; Hazim Kemal Ekenel

doi:10.1109/SIU.2018.8404417

Derin Öǧrenme Modelleri ile Eskiz Siniflandirma

Fevziye Irem Eyiokur
, Dogucan Yaman
, Hazim Kemal Ekenel

Bilgisayar Mühendisliği Bölümü

Istanbul Technical University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

2 Atıf (Scopus)

Özet

Sketch classification problem is challenging due to several reasons, such as absence of color and texture information, lack of detailed information of objects, and the quality, which depends on drawing ability of the person. In this study, sketch classification problem is addressed by using deep convolutional neural network models. Specifically, the effect of domain adaptation is examined, when fine-tuning the convolutional neural networks for sketch classification. By employing domain adaptation, the classification accuracy is increased by around 3%. The proposed system, which utilizes VGG-16 network model and performs two-stage fine-tuning, outperforms the previous state-of-the-art approaches on the TU Berlin sketch dataset by reaching 79,72% accuracy.

Tercüme edilen katkı başlığı	Sketch classification with deep learning models
Orijinal dil	Türkçe
Ana bilgisayar yayını başlığı	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
Sayfalar	1-4
Sayfa sayısı	4
ISBN (Elektronik)	9781538615010
DOI'lar	https://doi.org/10.1109/SIU.2018.8404417
Yayın durumu	Yayınlandı - 5 Tem 2018
Etkinlik	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 - Izmir, Türkiye Süre: 2 May 2018 → 5 May 2018

Yayın serisi

Adı	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
Ülke/Bölge	Türkiye
Şehir	Izmir
Periyot	2/05/18 → 5/05/18

Bibliyografik not

Publisher Copyright:
© 2018 IEEE.

Keywords

Convolutional neural network
Deep learning
Sketch classification

Belgeye Erişim

10.1109/SIU.2018.8404417

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Eyiokur, F. I., Yaman, D., & Ekenel, H. K. (2018). Derin Öǧrenme Modelleri ile Eskiz Siniflandirma. In 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 (pp. 1-4). (26th IEEE Signal Processing and Communications Applications Conference, SIU 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU.2018.8404417

@inproceedings{7bf0aa09fe624c2ab60380aa7a17b6a1,

title = "Derin {\"O}ǧrenme Modelleri ile Eskiz Siniflandirma",

abstract = "Sketch classification problem is challenging due to several reasons, such as absence of color and texture information, lack of detailed information of objects, and the quality, which depends on drawing ability of the person. In this study, sketch classification problem is addressed by using deep convolutional neural network models. Specifically, the effect of domain adaptation is examined, when fine-tuning the convolutional neural networks for sketch classification. By employing domain adaptation, the classification accuracy is increased by around 3\%. The proposed system, which utilizes VGG-16 network model and performs two-stage fine-tuning, outperforms the previous state-of-the-art approaches on the TU Berlin sketch dataset by reaching 79,72\% accuracy.",

keywords = "Convolutional neural network, Deep learning, Sketch classification",

author = "Eyiokur, \{Fevziye Irem\} and Dogucan Yaman and Ekenel, \{Hazim Kemal\}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 ; Conference date: 02-05-2018 Through 05-05-2018",

year = "2018",

month = jul,

day = "5",

doi = "10.1109/SIU.2018.8404417",

language = "T{\"u}rk{\c c}e",

series = "26th IEEE Signal Processing and Communications Applications Conference, SIU 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--4",

booktitle = "26th IEEE Signal Processing and Communications Applications Conference, SIU 2018",

address = "United States",

}

Eyiokur, FI, Yaman, D & Ekenel, HK 2018, Derin Öǧrenme Modelleri ile Eskiz Siniflandirma. in 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018. 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, Izmir, Türkiye, 2/05/18. https://doi.org/10.1109/SIU.2018.8404417

Derin Öǧrenme Modelleri ile Eskiz Siniflandirma. / Eyiokur, Fevziye Irem; Yaman, Dogucan; Ekenel, Hazim Kemal.
26th IEEE Signal Processing and Communications Applications Conference, SIU 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-4 (26th IEEE Signal Processing and Communications Applications Conference, SIU 2018).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Derin Öǧrenme Modelleri ile Eskiz Siniflandirma

AU - Eyiokur, Fevziye Irem

AU - Yaman, Dogucan

AU - Ekenel, Hazim Kemal

PY - 2018/7/5

Y1 - 2018/7/5

N2 - Sketch classification problem is challenging due to several reasons, such as absence of color and texture information, lack of detailed information of objects, and the quality, which depends on drawing ability of the person. In this study, sketch classification problem is addressed by using deep convolutional neural network models. Specifically, the effect of domain adaptation is examined, when fine-tuning the convolutional neural networks for sketch classification. By employing domain adaptation, the classification accuracy is increased by around 3%. The proposed system, which utilizes VGG-16 network model and performs two-stage fine-tuning, outperforms the previous state-of-the-art approaches on the TU Berlin sketch dataset by reaching 79,72% accuracy.

AB - Sketch classification problem is challenging due to several reasons, such as absence of color and texture information, lack of detailed information of objects, and the quality, which depends on drawing ability of the person. In this study, sketch classification problem is addressed by using deep convolutional neural network models. Specifically, the effect of domain adaptation is examined, when fine-tuning the convolutional neural networks for sketch classification. By employing domain adaptation, the classification accuracy is increased by around 3%. The proposed system, which utilizes VGG-16 network model and performs two-stage fine-tuning, outperforms the previous state-of-the-art approaches on the TU Berlin sketch dataset by reaching 79,72% accuracy.

KW - Convolutional neural network

KW - Deep learning

KW - Sketch classification

UR - https://www.scopus.com/pages/publications/85050795575

U2 - 10.1109/SIU.2018.8404417

DO - 10.1109/SIU.2018.8404417

M3 - Konferans katkısı

AN - SCOPUS:85050795575

T3 - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

SP - 1

EP - 4

BT - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

Y2 - 2 May 2018 through 5 May 2018

ER -

Derin Öǧrenme Modelleri ile Eskiz Siniflandirma

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Keywords

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap