Calibrated confidences and prediction sets for open set SAR ATR

Sudarshan Chakravarthy; Mark Ashby; Edmund Zelnio

doi:10.1117/12.3021865

7 June 2024 Calibrated confidences and prediction sets for open set SAR ATR

Sudarshan Chakravarthy, Mark Ashby, Edmund Zelnio

Proceedings Volume 13032, Algorithms for Synthetic Aperture Radar Imagery XXXI; 130320W (2024) https://doi.org/10.1117/12.3021865
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

Deep learning is a technology that has proven extremely effective at addressing difficult problems in the field of computer vision. Much of the recent research in Automatic Target Recognition has leveraged deep learning classifiers, which perform well in closed set problems but lack robustness in open set problems. Moreover, deep learning classifiers generally lack confidence estimates that accurately reflect their performance. This paper demonstrates recent research on calibrating confidence measures of deep learners on both closed and open set problems in a transfer learning setting where only a small amount of measured data is used during training and calibration. Furthermore, the calibrated confidences are used to generate statistically rigorous prediction sets, which include the true target at a user-defined error rate.

Citation Download Citation

Sudarshan Chakravarthy, Mark Ashby, and Edmund Zelnio "Calibrated confidences and prediction sets for open set SAR ATR", Proc. SPIE 13032, Algorithms for Synthetic Aperture Radar Imagery XXXI, 130320W (7 June 2024); https://doi.org/10.1117/12.3021865

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