Out-of-distribution detection for SAR imagery using ATR systems

Charles Hill

doi:10.1117/12.3013850

7 June 2024 Out-of-distribution detection for SAR imagery using ATR systems

Charles Hill

Proceedings Volume 13032, Algorithms for Synthetic Aperture Radar Imagery XXXI; 130320N (2024) https://doi.org/10.1117/12.3013850
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

A typical assumption for deploying machine learning models is that the model training and inference data were drawn from the same distribution. However, this assumption rarely holds true for systems deployed in the open world. Inference data can drift over time for numerous reasons, such as changes in operating conditions, adversarial modifications to targets, or sensor degradation. Despite these changes, deep learning models are especially vulnerable to issuing over-confident predictions on out-of-distribution data. This work seeks to address this issue by proposing a framework for describing out-of-distribution detection pipelines, proposing an out-of-distribution detection algorithm using Gaussian Mixture Models which is well suited for SAR ATR, and by evaluating multiple pipelines which exploit the intermediate states of ATR model deep neural networks. This work studies candidate pipelines with varied amounts of dimensionality reduction and detection algorithms on the SAMPLE+ dataset challenge problems for clutter and confuser rejection. Despite the exclusion of out-of-distribution samples from pipeline training, the presented results demonstrate that these samples can nonetheless be reliably detected, exceeding baseline performance by more than 10 percentage points.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Charles Hill "Out-of-distribution detection for SAR imagery using ATR systems", Proc. SPIE 13032, Algorithms for Synthetic Aperture Radar Imagery XXXI, 130320N (7 June 2024); https://doi.org/10.1117/12.3013850

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