Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/341504
Type: Artigo
Title: The multi-lane capsule network
Author: do Rosario, Vanderson Martins
Borin, Edson
Breternitz Jr., Mauricio
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
Subject: Aprendizado profundo
Country: Estados Unidos
Editor: Institute of Electrical and Electronics Engineers
Rights: Fechado
Identifier DOI: 10.1109/LSP.2019.2915661
Address: https://ieeexplore.ieee.org/document/8709729
Date Issue: 2019
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
000470063400001.pdf962.8 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.