# Deep multi-prototype capsule networks

arXiv: https://arxiv.org/abs/2404.15445 · HTML: https://mlsanity.com/paper/2404.15445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [Capsule Network Performance on Complex Data](https://mlsanity.com/paper/1712.03480/) (2017)
- [Capsule Networks Need an Improved Routing Algorithm](https://mlsanity.com/paper/1907.13327/) (2019)
- [The Multi-Lane Capsule Network (MLCN)](https://mlsanity.com/paper/1902.08431/) (2019)
- [Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN)](https://mlsanity.com/paper/1908.03935/) (2019)

## Abstract (arXiv)

Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. The goal behind the network is to perform an inverse computer graphics task, and the network parameters are the mapping weights that transform parts into a whole. The trainability of capsule networks in complex data with high intra-class or intra-part variation is challenging. This paper presents a multi-prototype architecture for guiding capsule networks to represent the variations in the image parts. To this end, instead of considering a single capsule for each class and part, the proposed method employs several capsules (co-group capsules), capturing multiple prototypes of an object. In the final layer, co-group capsules compete, and their soft output is considered the target for a competitive cross-entropy loss. Moreover, in the middle layers, the most active capsules map to the next layer with a shared weight among the co-groups. Consequently, due to the reduction in parameters, implicit weight-sharing makes it possible to have more deep capsule network layers. The experimental results on MNIST, SVHN, C-Cube, CEDAR, MCYT, and UTSig datasets reveal that the proposed model outperforms others regarding image classification accuracy.