papers AI Learner
The Github is limit! Click to go to the new site.

The Multi-Lane Capsule Network

2019-02-22
Vanderson Martins do Rosario, Edson Borin, Mauricio Breternitz Jr

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.08431

PDF

http://arxiv.org/pdf/1902.08431


Similar Posts

Comments