Analysis and Learning of Capsule Networks Robust for Small Image Deformation

TLDR: This work proposes a method for reducing computational costs by enabling a single capsule to represent multiple object classes in CapsNet, and incorporates the ArcFace distance learning method in the error function.

Abstract: The Capsule Network (CapsNet) is a deep learning model proposed for image classification that is robust to pose of change of objects in images. A capsule is a vector representing the position, size and presence of an object. However, with CapsNet, the number of capsules increases, depending on the number of classification classes, and learning is computationally expensive. Thus, we propose a method for reducing computational costs by enabling a single capsule to represent multiple object classes. To learn the distance between classes, we incorporate the ArcFace distance learning method in the error function. In a preliminary experiment, the distribution of capsules was visualised by principal component analysis to demonstrate the validity of the proposed method. Using the MNIST and CIFAR-10 datasets, as well as an the affine transformed dataset, we compare the accuracy and learning time of the original CapsNet and proposed method. The results demonstrate that accuracy is improved by 2.74% on the CIFAR-10 dataset, and the learning time is reduced by more than 19% in both datasets.