# The Multi-Lane Capsule Network (MLCN)

arXiv: https://arxiv.org/abs/1902.08431 · HTML: https://mlsanity.com/paper/1902.08431/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2019.

## Built on by (most cited first, 5 of 5)

- [Quick-CapsNet (QCN): A fast alternative to Capsule Networks](https://mlsanity.com/paper/2510.07600/) (2025)
- [PDR-CapsNet: an Energy-Efficient Parallel Approach to Dynamic Routing in Capsule Networks](https://mlsanity.com/paper/2310.03212/) (2023)
- [Deep multi-prototype capsule networks](https://mlsanity.com/paper/2404.15445/) (2024)
- [Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network](https://mlsanity.com/paper/2511.05617/) (2025)
- [LE-CapsNet: A Light and Enhanced Capsule Network](https://mlsanity.com/paper/2511.11708/) (2025)

## Abstract (arXiv)

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.