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

Authors: David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
Published: 2018-12-23 | Updated: 2019-12-05

Source: https://arxiv.org/abs/1812.09707

PDF: https://arxiv.org/pdf/1812.09707

AIにより推定されたラベル

ロバスト性 マルチクラス分類 深層学習

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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.