An Efficient Agreement Mechanism in CapsNets By Pairwise Product

04/01/2020
by   Lei Zhao, et al.
0

Capsule networks (CapsNets) are capable of modeling visual hierarchical relationships, which is achieved by the "routing-by-agreement" mechanism. This paper proposes a pairwise agreement mechanism to build capsules, inspired by the feature interactions of factorization machines (FMs). The proposed method has a much lower computation complexity. We further proposed a new CapsNet architecture that combines the strengths of residual networks in representing low-level visual features and CapsNets in modeling the relationships of parts to wholes. We conduct comprehensive experiments to compare the routing algorithms, including dynamic routing, EM routing, and our proposed FM agreement, based on both architectures of original CapsNet and our proposed one, and the results show that our method achieves both excellent performance and efficiency under a variety of situations.

READ FULL TEXT

page 4

page 6

page 7

research
05/27/2019

Capsule Routing via Variational Bayes

Capsule Networks are a recently proposed alternative for constructing Ne...
research
05/21/2019

Limitations of routing-by-agreement based capsule networks

Classical neural networks add a bias term to the sum of all weighted inp...
research
02/21/2018

Algebra and geometry of tensors for modeling rater agreement data

We study three different quasi-symmetry models and three different mixtu...
research
04/04/2022

REM: Routing Entropy Minimization for Capsule Networks

Capsule Networks ambition is to build an explainable and biologically-in...
research
08/11/2018

Neural Network Encapsulation

A capsule is a collection of neurons which represents different variants...
research
09/27/2019

Learning to compute inner consensus -- A noble approach to modeling agreement between Capsules

This project considers Capsule Networks, a recently introduced machine l...
research
02/26/2019

TCDCaps: Visual Tracking via Cascaded Dense Capsules

The critical challenge in tracking-by-detection framework is how to avoi...

Please sign up or login with your details

Forgot password? Click here to reset