English

The Multi-Lane Capsule Network (MLCN)

Computer Vision and Pattern Recognition 2019-09-04 v1 Machine Learning Image and Video Processing

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.

Keywords

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}
}
R2 v1 2026-06-23T07:48:03.973Z