CosGCN: cosine Gaussian capsule networks for few-shot learning

xuelin Wang; chengshuai Li; shujuan Liu; yonghong Chen; JianPing Xing

doi:10.1117/12.2636465

6 May 2022 CosGCN: cosine Gaussian capsule networks for few-shot learning

xuelin Wang, chengshuai Li, shujuan Liu, yonghong Chen, JianPing Xing

Proceedings Volume 12176, International Conference on Algorithms, Microchips and Network Applications; 121761V (2022) https://doi.org/10.1117/12.2636465
Event: International Conference on Algorithms, Microchips, and Network Applications 2022, 2022, Zhuhai, China

Abstract

This paper firstly researches the few-shot learning technology and the capsule routing theories. The iterative consistency mechanism of dynamic capsule routing is combined with the prototype network to design a better generalization performance. And a few-shot image classification model with better robustness for the posture of the sample in the test is proposed. In view of the defects in it, a multi-marginal cosine loss function is proposed for the model. Finally, the CosGCN model is proposed to ensure recognition accuracy and improve the computational efficiency of the model training. Experiments are carried out on the small sample dataset Omniglot and miniImagenet datasets. The results show that the model has better posture robustness.

Citation Download Citation

xuelin Wang, chengshuai Li, shujuan Liu, yonghong Chen, and JianPing Xing "CosGCN: cosine Gaussian capsule networks for few-shot learning", Proc. SPIE 12176, International Conference on Algorithms, Microchips and Network Applications, 121761V (6 May 2022); https://doi.org/10.1117/12.2636465

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