An Efficient Agreement Mechanism in CapsNets By Pairwise Product
This addresses efficiency bottlenecks in capsule networks for computer vision, though it appears incremental as it builds on existing routing methods.
The paper tackles the computational complexity of capsule networks' routing-by-agreement mechanism by proposing a pairwise agreement method inspired by factorization machines, which achieves both excellent performance and efficiency in experiments.
Capsule networks (CapsNets) are capable of modeling visual hierarchical relationships, which is achieved by the "routing-by-agreement" mechanism. This paper proposes a pairwise agreement mechanism to build capsules, inspired by the feature interactions of factorization machines (FMs). The proposed method has a much lower computation complexity. We further proposed a new CapsNet architecture that combines the strengths of residual networks in representing low-level visual features and CapsNets in modeling the relationships of parts to wholes. We conduct comprehensive experiments to compare the routing algorithms, including dynamic routing, EM routing, and our proposed FM agreement, based on both architectures of original CapsNet and our proposed one, and the results show that our method achieves both excellent performance and efficiency under a variety of situations.