ROBUSTCAPS: A TRANSFORMATION-ROBUST CAPSULE NETWORK FOR IMAGE CLASSIFICATION

S Balasubramanian, Sairaam Venkatraman, Raghunatha Sarma Rachakonda

Abstract: Geometric transformations of the training data as well as the test data present challenges to the use of deep neural networks to vision-based learning tasks. To address this issue, we present a deep neural network model that exhibits the desirable property of transformationrobustness. Our model, termed RobustCaps, uses group-equivariant convolutions in an improved capsule network model. RobustCaps uses a global context-normalised procedure in its routing algorithm to learn transformation-invariant part-whole relationships within image data. This learning of such relationships allows our model to outperform both capsule and convolutional neural network baselines on transformation-robust classification tasks. Specifically, RobustCaps achieves state-of-the-art accuracies on CIFAR-10, FashionMNIST, and CIFAR-100 when the images in these datasets are subjected to train and test-time rotations and translations.