Using dynamic routing to extract intermediate features for developing scalable capsule networks
arXiv:1907.06062
Abstract
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.
arXiv commentSecond International Conference on Advanced Computational and Communication Paradigms held at Sikkim Manipal Institute of Technology, Sikkim, India during February 25 - 28 , 2019
References in corpus (5)
- Capsule Network Performance on Complex Data
- Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach
- Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier
- An Enhanced Harmony Search Method for Bangla Handwritten Character Recognition Using Region Sampling
- An MLP based Approach for Recognition of Handwritten `Bangla' Numerals