Português
Ciência_Iscte
Publications
Publication Detailed Description
The multi-lane capsule network (MLCN)
Journal Title
IEEE Signal Processing Letters
Year (definitive publication)
2019
Language
English
Country
United States of America
More Information
Web of Science®
Scopus
Google Scholar
This publication is not indexed in Overton
Abstract
We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing while achieving high accuracy at reduced cost. A MLCN is composed of a number of (distinct) parallel lanes, each contributing to a dimension of the result, trained using the routing-by-agreement organization of CapsNet. Our results indicate similar accuracy with a much-reduced cost in number of parameters for the Fashion-MNIST and Cifar10 datasets. They also indicate that the MLCN outperforms the original CapsNet when using a proposed novel configuration for the lanes. MLCN also has faster training and inference times, being more than two-fold faster than the original CapsNet in a same accelerator.
Acknowledgements
--
Keywords
Capsule network,Multi-lane,Deep learning,CNN
Fields of Science and Technology Classification
- Electrical Engineering, Electronic Engineering, Information Engineering - Engineering and Technology
Funding Records
| Funding Reference | Funding Entity |
|---|---|
| 001 | CAPES |
| 313012/2017-2 | CNPq |
| UID/CEC/50021/2019 | Fundação para a Ciência e a Tecnologia |
| CCES2013/08293-7 | Fapesp |
| UID/MULTI/0446/2013 | Fundação para a Ciência e a Tecnologia |
