Assessing Capsule Networks With Biased Data
This work addresses the problem of robustness to biased data for machine learning practitioners, but it is incremental as it focuses on evaluating existing methods rather than introducing new ones.
The paper assessed the tolerance of Capsule Networks to biased data, specifically imbalanced training data and unfamiliar affine transformations, and compared them to Convolutional Neural Networks, finding that Capsule Networks showed varying robustness but provided new insights into their behavior.
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.