Robustcaps: a transformation-robust capsule network for image classification
This addresses the challenge of transformation-robustness in image classification for computer vision applications, representing an incremental improvement over existing capsule and convolutional neural network methods.
The paper tackles the problem of geometric transformations in image data by proposing RobustCaps, a capsule network with group-equivariant convolutions and a global context-normalized routing algorithm, which achieves state-of-the-art accuracies on CIFAR-10, FashionMNIST, and CIFAR-100 under train and test-time rotations and translations.
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. In order to address this issue, we present a deep neural network model that exhibits the desirable property of transformation-robustness. 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.