Wasserstein Routed Capsule Networks
This work addresses the challenge of making capsule networks more competitive for image classification tasks, representing an incremental advancement in the field.
The paper tackles the problem of capsule networks underperforming on image datasets by proposing a parameter-efficient architecture that uses a Wasserstein objective for dynamic capsule selection, achieving over 1.2% improvement on CIFAR-10 with fewer parameters.
Capsule networks offer interesting properties and provide an alternative to today's deep neural network architectures. However, recent approaches have failed to consistently achieve competitive results across different image datasets. We propose a new parameter efficient capsule architecture, that is able to tackle complex tasks by using neural networks trained with an approximate Wasserstein objective to dynamically select capsules throughout the entire architecture. This approach focuses on implementing a robust routing scheme, which can deliver improved results using little overhead. We perform several ablation studies verifying the proposed concepts and show that our network is able to substantially outperform other capsule approaches by over 1.2 % on CIFAR-10, using fewer parameters.