A Comparative Study of Routing Methods in Capsule Networks
Recently, the deep neural network structure caps-net was proposed by Sabouret al. [11]. Capsule networks are designed to learn relative geometry betweenthe features of a layer and the features of the next layer. The Capsule network’smain building blocks are capsules, which are represented by vectors...
Main Author: | Malmgren, Christoffer |
---|---|
Format: | Others |
Language: | English |
Published: |
Linköpings universitet, Datorseende
2019
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-156673 |
Similar Items
-
Towards Understanding Capsule Networks
by: Edstedt, Johan
Published: (2020) -
Recent Development of Computer Vision Technology to Improve Capsule Endoscopy
by: Junseok Park, et al.
Published: (2019-07-01) -
Cv-CapsNet: Complex-Valued Capsule Network
by: Xinming Cheng, et al.
Published: (2019-01-01) -
Multi-Task Learning using Road Surface Condition Classification and Road Scene Semantic Segmentation
by: Westell, Jesper
Published: (2019) -
DE-CapsNet: A Diverse Enhanced Capsule Network with Disperse Dynamic Routing
by: Bohan Jia, et al.
Published: (2020-01-01)