The Multi-Lane Capsule Network (MLCN)
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 datsets. 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 the same accelerator.
Cite
@article{arxiv.1902.08431,
title = {The Multi-Lane Capsule Network (MLCN)},
author = {Vanderson Martins do Rosario and Edson Borin and Mauricio Breternitz},
journal= {arXiv preprint arXiv:1902.08431},
year = {2019}
}