Improved ATR performance using boosting and transfer learning for adaptation of a target detection network

Robert Muise; Bruce McIntosh; Abhijit Mahalanobis

doi:10.1117/12.2587934

12 April 2021 Improved ATR performance using boosting and transfer learning for adaptation of a target detection network

Robert Muise, Bruce McIntosh, Abhijit Mahalanobis

Author Affiliations +

Proceedings Volume 11729, Automatic Target Recognition XXXI; 1172907 (2021) https://doi.org/10.1117/12.2587934
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

In this paper, we present preliminary results of infra-red target detection using a target-to-clutter based deep learning network (TCRnet). We augment this network with a separate processing path to render a new Directed Acyclic Graph network (TCRDAG) amenable to transfer learning. This transfer learning is used for network adaptation to new observations. The ROC curve shows significant improvement, particularly at the right side of the ROC curve. We further explore a boosting paradigm to improve the ROC curve for the left side. We then present results on a publicly available MWIR dataset released by NVESD.

Conference Presentation

Citation Download Citation

Robert Muise, Bruce McIntosh, and Abhijit Mahalanobis "Improved ATR performance using boosting and transfer learning for adaptation of a target detection network", Proc. SPIE 11729, Automatic Target Recognition XXXI, 1172907 (12 April 2021); https://doi.org/10.1117/12.2587934

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