Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem

Alican Mertan; Damien Jade Duff; Gozde Unal

doi:10.1109/SIU49456.2020.9302314

Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem

Alican Mertan, Damien Jade Duff, Gozde Unal

Yapay Zeka ve Veri Mühendisliği Bölümü

Istanbul Technical University

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

1 Atıf (Scopus)

Özet

We present a formulation of the relative depth estimation from a single image problem, as a ranking problem. By reformulating the problem this way, we were able to utilize literature on the ranking problem, and apply the existing knowledge to achieve better results. To this end, we have introduced a listwise ranking loss borrowed from ranking literature, weighted ListMLE, to the relative depth estimation problem. We have also brought a new metric which considers pixel depth ranking accuracy, on which our method is stronger.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)	9781728172064
DOI'lar	https://doi.org/10.1109/SIU49456.2020.9302314
Yayın durumu	Yayınlandı - 5 Eki 2020
Etkinlik	28th Signal Processing and Communications Applications Conference, SIU 2020 - Gaziantep, Turkey Süre: 5 Eki 2020 → 7 Eki 2020

Yayın serisi

Adı	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

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

???event.eventtypes.event.conference???	28th Signal Processing and Communications Applications Conference, SIU 2020
Ülke/Bölge	Turkey
Şehir	Gaziantep
Periyot	5/10/20 → 7/10/20

Bibliyografik not

Publisher Copyright:
© 2020 IEEE.

Finansman

The work is supported by the Scientific and Technological Research Council of Turkey (TÜBITAK), project 116E167.

Finansörler	Finansör numarası
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu	116E167

Belgeye Erişim

10.1109/SIU49456.2020.9302314

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Mertan, A., Duff, D. J., & Unal, G. (2020). Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings Makale 9302314 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU49456.2020.9302314

Mertan, Alican ; Duff, Damien Jade ; Unal, Gozde. / Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem. 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

@inproceedings{5d38487b5a4344a287e8e789c0b5c038,

title = "Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem",

abstract = "We present a formulation of the relative depth estimation from a single image problem, as a ranking problem. By reformulating the problem this way, we were able to utilize literature on the ranking problem, and apply the existing knowledge to achieve better results. To this end, we have introduced a listwise ranking loss borrowed from ranking literature, weighted ListMLE, to the relative depth estimation problem. We have also brought a new metric which considers pixel depth ranking accuracy, on which our method is stronger.",

keywords = "deep learning, depth estimation, learning to rank, relative depth estimation",

author = "Alican Mertan and Duff, {Damien Jade} and Gozde Unal",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 28th Signal Processing and Communications Applications Conference, SIU 2020 ; Conference date: 05-10-2020 Through 07-10-2020",

year = "2020",

month = oct,

day = "5",

doi = "10.1109/SIU49456.2020.9302314",

language = "English",

series = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

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

booktitle = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

address = "United States",

}

Mertan, A, Duff, DJ & Unal, G 2020, Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem. in 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings., 9302314, 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Turkey, 5/10/20. https://doi.org/10.1109/SIU49456.2020.9302314

Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem. / Mertan, Alican; Duff, Damien Jade; Unal, Gozde.
2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9302314 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

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

TY - GEN

T1 - Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem

AU - Mertan, Alican

AU - Duff, Damien Jade

AU - Unal, Gozde

PY - 2020/10/5

Y1 - 2020/10/5

N2 - We present a formulation of the relative depth estimation from a single image problem, as a ranking problem. By reformulating the problem this way, we were able to utilize literature on the ranking problem, and apply the existing knowledge to achieve better results. To this end, we have introduced a listwise ranking loss borrowed from ranking literature, weighted ListMLE, to the relative depth estimation problem. We have also brought a new metric which considers pixel depth ranking accuracy, on which our method is stronger.

AB - We present a formulation of the relative depth estimation from a single image problem, as a ranking problem. By reformulating the problem this way, we were able to utilize literature on the ranking problem, and apply the existing knowledge to achieve better results. To this end, we have introduced a listwise ranking loss borrowed from ranking literature, weighted ListMLE, to the relative depth estimation problem. We have also brought a new metric which considers pixel depth ranking accuracy, on which our method is stronger.

KW - deep learning

KW - depth estimation

KW - learning to rank

KW - relative depth estimation

UR - http://www.scopus.com/inward/record.url?scp=85100294326&partnerID=8YFLogxK

U2 - 10.1109/SIU49456.2020.9302314

DO - 10.1109/SIU49456.2020.9302314

M3 - Conference contribution

AN - SCOPUS:85100294326

T3 - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

BT - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 28th Signal Processing and Communications Applications Conference, SIU 2020

Y2 - 5 October 2020 through 7 October 2020

ER -

Mertan A, Duff DJ, Unal G. Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9302314. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). doi: 10.1109/SIU49456.2020.9302314

Siralama Sorunu Olarak Nispi Derinlik Tahmini Relative Depth Estimation as a Ranking Problem

Özet

Yayın serisi

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

Bibliyografik not

Finansman

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap