Capsule routing based on Dirichlet process mixture model

Ning Wang; Ling Wang

doi:10.1117/12.2637155

15 June 2022 Capsule routing based on Dirichlet process mixture model

Ning Wang, Ling Wang

Proceedings Volume 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022); 122850V (2022) https://doi.org/10.1117/12.2637155
Event: International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 2022, Zhuhai, China

Abstract

Capsule networks have a new network structure that combines unsupervised learning method with the convolutional neural networks. Compared with convolutional neural networks, its advantage lies in its generalization ability to a novel viewpoint. In this paper, we combined the Dirichlet process mixture model with the capsule network, and use the coordinate ascending algorithm to realize the information transfer between capsule layers. We use a shallow network to verify the model’s generalization ability for a different viewpoint on the SmallNORB and BUAA-SID datasets. The comparison shows that our method has a lower test error than the Gaussian mixture model that is directly inferred by approximation.

Citation Download Citation

Ning Wang and Ling Wang "Capsule routing based on Dirichlet process mixture model", Proc. SPIE 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 122850V (15 June 2022); https://doi.org/10.1117/12.2637155

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available