RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks

by   Alberto Marchisio, et al.
NYU college
Politecnico di Torino
TU Wien

Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. Other than achieving high accuracy, another relevant factor in deploying CapsNets in safety-critical applications is the robustness against input transformations and malicious adversarial attacks. In this paper, we systematically analyze and evaluate different factors affecting the robustness of CapsNets, compared to traditional Convolutional Neural Networks (CNNs). Towards a comprehensive comparison, we test two CapsNet models and two CNN models on the MNIST, GTSRB, and CIFAR10 datasets, as well as on the affine-transformed versions of such datasets. With a thorough analysis, we show which properties of these architectures better contribute to increasing the robustness and their limitations. Overall, CapsNets achieve better robustness against adversarial examples and affine transformations, compared to a traditional CNN with a similar number of parameters. Similar conclusions have been derived for deeper versions of CapsNets and CNNs. Moreover, our results unleash a key finding that the dynamic routing does not contribute much to improving the CapsNets' robustness. Indeed, the main generalization contribution is due to the hierarchical feature learning through capsules.


page 1

page 2

page 5


Improving the Robustness of Capsule Networks to Image Affine Transformations

Convolutional neural networks (CNNs) achieve translational invariance us...

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

Capsule Networks envision an innovative point of view about the represen...

Security Analysis of Capsule Network Inference using Horizontal Collaboration

The traditional convolution neural networks (CNN) have several drawbacks...

Extreme Value Preserving Networks

Recent evidence shows that convolutional neural networks (CNNs) are bias...

Affine Disentangled GAN for Interpretable and Robust AV Perception

Autonomous vehicles (AV) have progressed rapidly with the advancements i...

Capsule Network is Not More Robust than Convolutional Network

The Capsule Network is widely believed to be more robust than Convolutio...

Affine-Transformation-Invariant Image Classification by Differentiable Arithmetic Distribution Module

Although Convolutional Neural Networks (CNNs) have achieved promising re...

Please sign up or login with your details

Forgot password? Click here to reset