Capsule Routing via Variational Bayes
This work addresses inherent weaknesses in capsule networks for researchers in computer vision, offering a novel method that enhances performance and generalization, though it is incremental as it builds on existing routing-by-agreement concepts.
The paper tackled the problem of improving capsule networks by proposing a new routing algorithm derived from Variational Bayes to model uncertainty over capsule pose parameters, resulting in outperforming state-of-the-art on smallNORB with 50% fewer capsules and achieving competitive performances on multiple datasets.
Capsule networks are a recently proposed type of neural network shown to outperform alternatives in challenging shape recognition tasks. In capsule networks, scalar neurons are replaced with capsule vectors or matrices, whose entries represent different properties of objects. The relationships between objects and their parts are learned via trainable viewpoint-invariant transformation matrices, and the presence of a given object is decided by the level of agreement among votes from its parts. This interaction occurs between capsule layers and is a process called routing-by-agreement. In this paper, we propose a new capsule routing algorithm derived from Variational Bayes for fitting a mixture of transforming gaussians, and show it is possible transform our capsule network into a Capsule-VAE. Our Bayesian approach addresses some of the inherent weaknesses of MLE based models such as the variance-collapse by modelling uncertainty over capsule pose parameters. We outperform the state-of-the-art on smallNORB using 50% fewer capsules than previously reported, achieve competitive performances on CIFAR-10, Fashion-MNIST, SVHN, and demonstrate significant improvement in MNIST to affNIST generalisation over previous works.