Kernelized Capsule Networks
Abstract
Capsule Networks attempt to represent patterns in images in a way that preserves hierarchical spatial relationships. Additionally, research has demonstrated that these techniques may be robust against adversarial perturbations. We present an improvement to training capsule networks with added robustness via non-parametric kernel methods. The representations learned through the capsule network are used to construct covariance kernels for Gaussian processes (GPs). We demonstrate that this approach achieves comparable prediction performance to Capsule Networks while improving robustness to adversarial perturbations and providing a meaningful measure of uncertainty that may aid in the detection of adversarial inputs.
Cite
@article{arxiv.1906.03164,
title = {Kernelized Capsule Networks},
author = {Taylor Killian and Justin Goodwin and Olivia Brown and Sung-Hyun Son},
journal= {arXiv preprint arXiv:1906.03164},
year = {2019}
}
Comments
Paper accepted to the ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning