Capsule network with shortcut routing

Abstract

This study introduces "shortcut routing," a novel routing mechanism in capsule networks that addresses computational inefficiencies by directly activating global capsules from local capsules, eliminating intermediate layers. An attention-based approach with fuzzy coefficients is also explored for improved efficiency. Experimental results on Mnist, smallnorb, and affNist datasets show comparable classification performance, achieving accuracies of 99.52%, 93.91%, and 89.02% respectively. The proposed fuzzy-based and attention-based routing methods significantly reduce the number of calculations by 1.42 and 2.5 times compared to EM routing, highlighting their computational advantages in capsule networks. These findings contribute to the advancement of efficient and accurate hierarchical pattern representation models.

arXiv comment8 pages, published at IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences E104.A(8)

References in corpus (10)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Explaining and Harnessing Adversarial Examples
• Deep Convolutional Inverse Graphics Network
• Group Equivariant Convolutional Networks
• Capsules for Object Segmentation
• Investigating Capsule Networks with Dynamic Routing for Text Classification
• Group Equivariant Capsule Networks
• CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces
• VideoCapsuleNet: A Simplified Network for Action Detection
• Multi-labeled Relation Extraction with Attentive Capsule Network