Generalized Capsule Networks with Trainable Routing Procedure

Zhenhua Chen, Chuhua Wang, Tiancong Zhao, David Crandall

Abstract: CapsNet (Capsule Network) was first proposed by Sabour et al. (2017) and lateranother version of CapsNet was proposed by Hinton et al. (2018). CapsNet hasbeen proved effective in modeling spatial features with much fewer parameters.However, the routing procedures (dynamic routing and EM routing) in both pa-pers are not well incorporated into the whole training process, and the optimalnumber for the routing procedure has to be found manually. We propose Gen-eralized GapsNet (G-CapsNet) to overcome this disadvantages by incorporatingthe routing procedure into the optimization. We implement two versions of G-CapsNet (fully-connected and convolutional) on CAFFE (Jia et al. (2014)) andevaluate them by testing the accuracy on MNIST & CIFAR10, the robustness towhite-box & black-box attack, and the generalization ability on GAN-generatedsynthetic images. We also explore the scalability of G-CapsNet by constructinga relatively deep G-CapsNet. The experiment shows that G-CapsNet has goodgeneralization ability and scalability.

Keywords: Capsule networks, generalization, scalability, adversarial robustness

TL;DR: A scalable capsule network

Code: [ chenzhenhua986/CAFFE-CapsNet](https://github.com/chenzhenhua986/CAFFE-CapsNet)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1808.08692/code)