Grouping Capsules Based Different Types (1911.04820v1)

Abstract: Capsule network was introduced as a new architecture of neural networks, it encoding features as capsules to overcome the lacking of equivariant in the convolutional neural networks. It uses dynamic routing algorithm to train parameters in different capsule layers, but the dynamic routing algorithm need to be improved. In this paper, we propose a novel capsule network architecture and discussed the effect of initialization method of the coupling coefficient $c_{ij}$ on the model. First, we analyze the rate of change of the initial value of $c_{ij}$ when the dynamic routing algorithm iterates. The larger the initial value of $c_{ij}$, the better effect of the model. Then, we proposed improvement that training different types of capsules by grouping capsules based different types. And this improvement can adjust the initial value of $c_{ij}$ to make it more suitable. We experimented with our improvements on some computer vision datasets and achieved better results than the original capsule network