Corpus ID: 208139575

Increasing the adversarial robustness and explainability of capsule networks with $\gamma$-capsules.

@article{Peer2019IncreasingTA,
  title={Increasing the adversarial robustness and explainability of capsule networks with \$\gamma\$-capsules.},
  author={David Peer and Sebastian Stabinger and Antonio Rodr{\'i}guez-S{\'a}nchez},
  journal={arXiv: Learning},
  year={2019}
}
  • David Peer, Sebastian Stabinger, Antonio Rodríguez-Sánchez
  • Published 2019
  • Mathematics, Computer Science
  • arXiv: Learning
  • In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior $\gamma$-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 $\gamma$-capsule networks and metrics for evaluation are also provided. Under our framework we show that common capsule networks do not necessarily… CONTINUE READING
    43
    Twitter Mentions

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 18 REFERENCES

    3D Point Capsule Networks

    VIEW 1 EXCERPT

    Adversarial Examples Are Not Bugs, They Are Features

    VIEW 1 EXCERPT

    DeepCaps: Going Deeper With Capsule Networks