A quantifiable testing of global translational invariance in Convolutional and Capsule Networks

Abstract

We design simple and quantifiable testing of global translation-invariance in deep learning models trained on the MNIST dataset. Experiments on convolutional and capsules neural networks show that both models have poor performance in dealing with global translation-invariance; however, the performance improved by using data augmentation. Although the capsule network is better on the MNIST testing dataset, the convolutional neural network generally has better performance on the translation-invariance.

Tasks

Reproductions