Quaternion capsule networks

Name: Quaternion capsule networks
Author: Özcan, Barış, Kınlı, Osman Furkan

İsim	Quaternion capsule networks
Yazar	Özcan, Barış, Kınlı, Osman Furkan
Basım Tarihi:	2021
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-1-7281-8808-9
Kayıt Numarası	1d698c85-b393-4673-a82b-ee4ca992bbe1
Lokasyon	Computer Science
Tarih	2021
Örnek Metin	Capsules are grouping of neurons that allow to represent sophisticated information of a visual entity such as pose and features. In the view of this property, Capsule Networks outperform CNNs in challenging tasks like object recognition in unseen viewpoints, and this is achieved by learning the transformations between the object and its parts with the help of high dimensional representation of pose information. In this paper, we present Quaternion Capsules (QCN) where pose information of capsules and their transformations are represented by quaternions. Quaternions arc immune to the gimbal lock, have straightforward regularization of the rotation representation for capsules, and require less number of parameters than matrices. The experimental results show that QCNs generalize better to novel viewpoints with fewer parameters, and also achieve onpar or better performances with the state-of-the-art Capsule architectures on well-known benchmarking datasets. Our code is available(1).
DOI	10.1109/ICPR48806.2021.9412006

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Quaternion capsule networks

Yazar Özcan, Barış, Kınlı, Osman Furkan

Basım Tarihi 2021

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-1-7281-8808-9

Kayıt Numarası 1d698c85-b393-4673-a82b-ee4ca992bbe1

Lokasyon Computer Science

Tarih 2021

Örnek Metin Capsules are grouping of neurons that allow to represent sophisticated information of a visual entity such as pose and features. In the view of this property, Capsule Networks outperform CNNs in challenging tasks like object recognition in unseen viewpoints, and this is achieved by learning the transformations between the object and its parts with the help of high dimensional representation of pose information. In this paper, we present Quaternion Capsules (QCN) where pose information of capsules and their transformations are represented by quaternions. Quaternions arc immune to the gimbal lock, have straightforward regularization of the rotation representation for capsules, and require less number of parameters than matrices. The experimental results show that QCNs generalize better to novel viewpoints with fewer parameters, and also achieve onpar or better performances with the state-of-the-art Capsule architectures on well-known benchmarking datasets. Our code is available(1).