Fashion image retrieval with capsule networks

Name: Fashion image retrieval with capsule networks
Author: Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

İsim	Fashion image retrieval with capsule networks
Yazar	Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan
Basım Tarihi:	2019
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-1-7281-5023-9
Kayıt Numarası	300972c8-03e9-4877-8a32-dda455a5d956
Lokasyon	Computer Science
Tarih	2019
Örnek Metin	In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connected (RC) blocks are used to form the input of capsule layers. Experimental results show that both of our designs outperform all variants of the baseline study, namely FashionNet, without relying on the landmark information. Moreover, when compared to the SOTA architectures on clothing retrieval, our proposed Triplet Capsule Networks achieve comparable recall rates only with half of parameters used in the SOTA architectures.
DOI	10.1109/ICCVW.2019.00376

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Fashion image retrieval with capsule networks

Yazar Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

Basım Tarihi 2019

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-1-7281-5023-9

Kayıt Numarası 300972c8-03e9-4877-8a32-dda455a5d956

Lokasyon Computer Science

Tarih 2019

Örnek Metin In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connected (RC) blocks are used to form the input of capsule layers. Experimental results show that both of our designs outperform all variants of the baseline study, namely FashionNet, without relying on the landmark information. Moreover, when compared to the SOTA architectures on clothing retrieval, our proposed Triplet Capsule Networks achieve comparable recall rates only with half of parameters used in the SOTA architectures.

DOI 10.1109/ICCVW.2019.00376