# Generalized Capsule Networks with Trainable Routing Procedure

arXiv: https://arxiv.org/abs/1808.08692 · HTML: https://mlsanity.com/paper/1808.08692/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 4 of 4)

- [Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules](https://mlsanity.com/paper/2111.07785/) (2021)
- [Graph Routing between Capsules](https://mlsanity.com/paper/2106.11531/) (2021)
- [Capsule networks with non-iterative cluster routing](https://mlsanity.com/paper/2109.09213/) (2021)
- [CapsNet for Medical Image Segmentation](https://mlsanity.com/paper/2203.08948/) (2022)

## Abstract (arXiv)

CapsNet (Capsule Network) was first proposed by~citetcapsule and later another version of CapsNet was proposed by~citetemrouting. CapsNet has been proved effective in modeling spatial features with much fewer parameters. However, the routing procedures in both papers are not well incorporated into the whole training process. The optimal number of routing procedure is misery which has to be found manually. To overcome this disadvantages of current routing procedures in CapsNet, we embed the routing procedure into the optimization procedure with all other parameters in neural networks, namely, make coupling coefficients in the routing procedure become completely trainable. We call it Generalized CapsNet (G-CapsNet). We implement both "full-connected" version of G-CapsNet and "convolutional" version of G-CapsNet. G-CapsNet achieves a similar performance in the dataset MNIST as in the original papers. We also test two capsule packing method (cross feature maps or with feature maps) from previous convolutional layers and see no evident difference. Besides, we also explored possibility of stacking multiple capsule layers. The code is shared on hyperlinkhttps://github.com/chenzhenhua986/CAFFE-CapsNetCAFFE-CapsNet.