English

Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption

Computer Vision and Pattern Recognition 2023-01-05 v1 Artificial Intelligence Machine Learning

Abstract

Capsule neural networks replace simple, scalar-valued neurons with vector-valued capsules. They are motivated by the pattern recognition system in the human brain, where complex objects are decomposed into a hierarchy of simpler object parts. Such a hierarchy is referred to as a parse-tree. Conceptually, capsule neural networks have been defined to realize such parse-trees. The capsule neural network (CapsNet), by Sabour, Frosst, and Hinton, is the first actual implementation of the conceptual idea of capsule neural networks. CapsNets achieved state-of-the-art performance on simple image recognition tasks with fewer parameters and greater robustness to affine transformations than comparable approaches. This sparked extensive follow-up research. However, despite major efforts, no work was able to scale the CapsNet architecture to more reasonable-sized datasets. Here, we provide a reason for this failure and argue that it is most likely not possible to scale CapsNets beyond toy examples. In particular, we show that the concept of a parse-tree, the main idea behind capsule neuronal networks, is not present in CapsNets. We also show theoretically and experimentally that CapsNets suffer from a vanishing gradient problem that results in the starvation of many capsules during training.

Keywords

Cite

@article{arxiv.2301.01583,
  title  = {Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption},
  author = {Matthias Mitterreiter and Marcel Koch and Joachim Giesen and Sören Laue},
  journal= {arXiv preprint arXiv:2301.01583},
  year   = {2023}
}

Comments

To appear in AAAI 2023

R2 v1 2026-06-28T08:02:26.197Z