Improving the Robustness of Capsule Networks to Image Affine Transformations

by   Jindong Gu, et al.

Convolutional neural networks (CNNs) achieve translational invariance using pooling operations, which do not maintain the spatial relationship in the learned representations. Hence, they cannot extrapolate their understanding of the geometric transformation of inputs. Recently, Capsule Networks (CapsNets) have been proposed to tackle this problem. In CapsNets, each entity is represented by a vector and routed to high-level entities by a dynamic routing algorithm. The CapsNets have been shown to be more robust than CNNs to affine transformations of inputs. However, there is still a huge gap between their performance on transformed inputs compared to untransformed versions. In this work, we first revisit the routing procedure by (un)rolling its forward and backward passes. Our investigation reveals that the routing procedure contributes neither to generalization ability nor to the affine robustness of the CapsNets. Furthermore, we explore the limitations of capsule transformations and propose affine CapsNets (Aff-CapsNets) that are more robust to affine transformations. On our benchmark task where models are trained on the MNIST dataset and tested on the AffNIST dataset, our Aff-CapsNets improve the benchmark performance by a large margin (from 79% to 93.21%), without using a routing mechanism. We also demonstrate the superiority of Aff-CapsNets on a real-world Brain Tumor Type classification task.


page 5

page 6

page 7

page 8


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

Capsule Networks (CapsNets) are able to hierarchically preserve the pose...

Assessing Capsule Networks With Biased Data

Machine learning based methods achieves impressive results in object cla...

Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification

Image classification is a challenging problem which aims to identify the...

Enabling equivariance for arbitrary Lie groups

Although provably robust to translational perturbations, convolutional n...

Capsule Network is Not More Robust than Convolutional Network

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

Interpretable Graph Capsule Networks for Object Recognition

Capsule Networks, as alternatives to Convolutional Neural Networks, have...

Polyphonic Sound Event Detection by using Capsule Neural Networks

Artificial sound event detection (SED) has the aim to mimic the human ab...

Please sign up or login with your details

Forgot password? Click here to reset