# How to Accelerate Capsule Convolutions in Capsule Networks

arXiv: https://arxiv.org/abs/2104.02621 · HTML: https://mlsanity.com/paper/2104.02621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 5 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 4 of 4)

- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Attention routing between capsules](https://mlsanity.com/paper/1907.01750/) (2019)
- [Neural Network Encapsulation](https://mlsanity.com/paper/1808.03749/) (2018)
- [Fast Dynamic Routing Based on Weighted Kernel Density Estimation](https://mlsanity.com/paper/1805.10807/) (2018)

## Abstract (arXiv)

How to improve the efficiency of routing procedures in CapsNets has been studied a lot. However, the efficiency of capsule convolutions has largely been neglected. Capsule convolution, which uses capsules rather than neurons as the basic computation unit, makes it incompatible with current deep learning frameworks' optimization solution. As a result, capsule convolutions are usually very slow with these frameworks. We observe that capsule convolutions can be considered as the operations of `multiplication of multiple small matrics' plus tensor-based combination. Based on this observation, we develop two acceleration schemes with CUDA APIs and test them on a custom CapsNet. The result shows that our solution achieves a 4X acceleration.