Multi-task learning for underwater object classification

J. R. Stack; F. Crosby; R. J. McDonald; Y. Xue; L. Carin

doi:10.1117/12.717071

26 April 2007 Multi-task learning for underwater object classification

J. R. Stack, F. Crosby, R. J. McDonald, Y. Xue, L. Carin

Proceedings Volume 6553, Detection and Remediation Technologies for Mines and Minelike Targets XII; 65530N (2007) https://doi.org/10.1117/12.717071
Event: Defense and Security Symposium, 2007, Orlando, Florida, United States

Abstract

The purpose of this research is to jointly learn multiple classification tasks by appropriately sharing information between similar tasks. In this setting, examples of different tasks include the discrimination of targets from non-targets by different sonars or by the same sonar operating in sufficiently different environments. This is known as multi-task learning (MTL) and is accomplished via a Bayesian approach whereby the learned parameters for classifiers of similar tasks are drawn from a common prior. To learn which tasks are similar and the appropriate priors a Dirichlet process is employed and solved using mean field variational Bayesian inference. The result is that for many real-world instances where training data is limited MTL exhibits a significant improvement over both learning individual classifiers for each task as well as pooling all data and training one overall classifier. The performance of this method is demonstrated on simulated data and experimental data from multiple imaging sonars operating over multiple environments.

Citation Download Citation

J. R. Stack, F. Crosby, R. J. McDonald, Y. Xue, and L. Carin "Multi-task learning for underwater object classification", Proc. SPIE 6553, Detection and Remediation Technologies for Mines and Minelike Targets XII, 65530N (26 April 2007); https://doi.org/10.1117/12.717071

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