# Increasing the adversarial robustness and explainability of capsule networks with γ-capsules

arXiv: https://arxiv.org/abs/1812.09707 · HTML: https://mlsanity.com/paper/1812.09707/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2018.

## Built on by (most cited first, 5 of 5)

- [Training Deep Capsule Networks with Residual Connections](https://mlsanity.com/paper/2104.07393/) (2021)
- [Auto-tuning of Deep Neural Networks by Conflicting Layer Removal](https://mlsanity.com/paper/2103.04331/) (2021)
- [Momentum Capsule Networks](https://mlsanity.com/paper/2201.11091/) (2022)
- [Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training](https://mlsanity.com/paper/2202.13755/) (2022)
- [Affordance detection with Dynamic-Tree Capsule Networks](https://mlsanity.com/paper/2211.05200/) (2022)

## Abstract (arXiv)

In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior γ-capsule networks. Our inductive bias that is inspired by TE neurons of the inferior temporal cortex increases the adversarial robustness and the explainability of capsule networks. A theoretical framework with formal definitions of γ-capsule networks and metrics for evaluation are also provided. Under our framework we show that common capsule networks do not necessarily make use of this inductive bias. For this reason we introduce a novel routing algorithm and use a different training algorithm to be able to implement γ-capsule networks. We then show experimentally that γ-capsule networks are indeed more transparent and more robust against adversarial attacks than regular capsule networks.