Survey on Capsule Network’s Depth Scalability and Learned Feature Spatial Relationships Retention


Manogaran, Ugenteraan and Wong, Ya Ping and Ng, Boon Yian (2022) Survey on Capsule Network’s Depth Scalability and Learned Feature Spatial Relationships Retention. Lecture Notes in Networks and Systems, 439. pp. 165-182. ISSN 2367-3370

Full text not available from this repository.


In 2017, the first working architecture of capsule networks called Capsule Network with Dynamic Routing (CapsNet) was introduced and shown to perform better than Convolutional Neural Networks (CNNs) in the MNIST dataset. It was also speculated that capsule networks’ ability to retain spatial relationships among learned features are better than CNNs. Ever since then, much research has been devoted to improving capsule network architectures. However, most proposed architectures are relatively shallow and not scalable depth-wise. Also, some works have shown that the said retention ability is not as good as speculated. In this survey, we reviewed research works on capsule networks that focus on depth scaling and the said retention ability. We found that the routing algorithm used in a capsule network plays a crucial role in both the depth scalability and the said retention ability. We believe that future research on capsule networks should be focused on improving the routing algorithm to ensure the success of capsule networks.

Item Type: Article
Uncontrolled Keywords: CapsNet, Convolutional neural network, Spatial relationships, Depth scalability
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75-76.95 Calculating machines
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 03 Nov 2022 02:03
Last Modified: 03 Nov 2022 02:03


Downloads per month over past year

View ItemEdit (login required)