# Assessing Capsule Networks With Biased Data

## TL;DR

This paper evaluates the robustness of Capsule Networks against biased and imbalanced training data, comparing their performance with CNNs in scenarios involving data imbalance and affine transformations.

## Contribution

It introduces two experimental scenarios to assess capsule networks' tolerance to biased data and their generalization to affine transformations, filling a research gap.

## Key findings

- Capsule Networks show different robustness levels compared to CNNs under data bias.
- Dynamic routing and EM routing affect the tolerance of capsule networks to biased data.
- Capsule Networks exhibit unique generalization behaviors with affine transformations.

## Abstract

Machine learning based methods achieves impressive results in object classification and detection. Utilizing representative data of the visual world during the training phase is crucial to achieve good performance with such data driven approaches. However, it not always possible to access bias-free datasets thus, robustness to biased data is a desirable property for a learning system. Capsule Networks have been introduced recently and their tolerance to biased data has received little attention. This paper aims to fill this gap and proposes two experimental scenarios to assess the tolerance to imbalanced training data and to determine the generalization performance of a model with unfamiliar affine transformations of the images. This paper assesses dynamic routing and EM routing based Capsule Networks and proposes a comparison with Convolutional Neural Networks in the two tested scenarios. The presented results provide new insights into the behaviour of capsule networks.