Learning to compute inner consensus: A novel approach to modeling agreement between Capsules
This work addresses a specific bottleneck in Capsule Networks for machine learning researchers, but appears incremental as it builds on existing routing concepts.
The authors tackled the limitation of fixed routing procedures in Capsule Networks by proposing two methods to learn routing as network parameters, aiming to enhance model expressiveness.
This project considers Capsule Networks, a recently introduced machine learning model that has shown promising results regarding generalization and preservation of spatial information with few parameters. The Capsule Network's inner routing procedures thus far proposed, a priori, establish how the routing relations are modeled, which limits the expressiveness of the underlying model. In this project, we propose two distinct ways in which the routing procedure can be learned like any other network parameter.