Using dynamic routing to extract intermediate features for developing scalable capsule networks
This work addresses scalability issues in capsule networks for researchers and practitioners, though it is incremental as it modifies an existing method.
The paper tackled the high computational complexity of dynamic routing in capsule networks by using it to extract intermediate features instead of output class capsules, resulting in faster computation and improved accuracy for problems with many classes.
Capsule networks have gained a lot of popularity in short time due to its unique approach to model equivariant class specific properties as capsules from images. However the dynamic routing algorithm comes with a steep computational complexity. In the proposed approach we aim to create scalable versions of the capsule networks that are much faster and provide better accuracy in problems with higher number of classes. By using dynamic routing to extract intermediate features instead of generating output class specific capsules, a large increase in the computational speed has been observed. Moreover, by extracting equivariant feature capsules instead of class specific capsules, the generalization capability of the network has also increased as a result of which there is a boost in accuracy.