Introducing Routing Uncertainty in Capsule Networks

Fabio De Sousa Ribeiro, Georgios Leontidis, Stefanos Kollias

Abstract:

Rather than performing inefficient local iterative routing between adjacent capsule
layers, we propose an alternative global view based on representing the inherent uncertainty in part-object assignment. In our formulation, the local routing iterations
are replaced with variational inference of part-object connections in a probabilistic
capsule network, leading to a significant speedup without sacrificing performance.
In this way, global context is also considered when routing capsules by introducing
global latent variables that have direct influence on the objective function, and
are updated discriminatively in accordance with the minimum description length
(MDL) principle. We focus on enhancing capsule network properties, and perform a
thorough evaluation on pose-aware tasks, observing improvements in performance
over previous approaches whilst being more computationally efficient