Deep multi-prototype capsule networks

TL;DR

This paper introduces a multi-prototype capsule network architecture that captures diverse image part variations, improves trainability, and enhances classification accuracy across multiple datasets.

Contribution

It proposes a multi-prototype capsule network with co-group capsules and shared weights, enabling deeper architectures and better handling of intra-class variations.

Findings

Outperforms existing models on MNIST, SVHN, and other datasets.

Allows deeper capsule networks due to parameter reduction.

Achieves higher classification accuracy.

Abstract

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.