A Receptor Skeleton for Capsule Neural Networks
Jintai Chen,u00a0Hongyun Yu,u00a0Chengde Qian,u00a0Danny Z Chen,u00a0Jian Wu
In previous Capsule Neural Networks (CapsNets), routing algorithms often performed clustering processes to assemble the child capsulesu2019 representations into parent capsules. Such routing algorithms were typically implemented with iterative processes and incurred high computing complexity. This paper presents a new capsule structure, which contains a set of optimizable receptors and a transmitter is devised on the capsuleu2019s representation. Specifically, child capsulesu2019 representations are sent to the parent capsules whose receptors match well the transmitters of the child capsulesu2019 representations, avoiding applying computationally complex routing algorithms. To ensure the receptors in a CapsNet work cooperatively, we build a skeleton to organize the receptors in different capsule layers in a CapsNet. The receptor skeleton assigns a share-out objective for each receptor, making the CapsNet perform as a hierarchical agglomerative clustering process. Comprehensive experiments verify that our approach facilitates efficient clustering processes, and CapsNets with our approach significantly outperform CapsNets with previous routing algorithms on image classification, affine transformation generalization, overlapped object recognition, and representation semantic decoupling.
