Graph pretraining approach to utilize synthetic data for SAR ATR

Caleb Parks; Susan Gauch; Matthew Scherreik; Ryan Socha

doi:10.1117/12.3025891

7 June 2024 Graph pretraining approach to utilize synthetic data for SAR ATR

Caleb Parks, Susan Gauch, Matthew Scherreik, Ryan Socha

Proceedings Volume 13032, Algorithms for Synthetic Aperture Radar Imagery XXXI; 130320X (2024) https://doi.org/10.1117/12.3025891
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

Because of limitations in availability of synthetic aperture radar (SAR) training data, automatic target recognition (ATR) researchers have turned to the use of synthetic SAR images. Unfortunately, training neural network classifiers on this synthetic data does not yield robust models. Assuming access to limited measured SAR data, we evaluate two natural, transfer-learning approaches to solve this problem, showing that both do not successfully lead to solutions. Motivated by the successes of contrastive, representation, and metric learning, we propose a novel graph-based pretraining approach to transfer knowledge from synthetic samples to real-world scenarios. We show that this approach is applicable to three different neural network architectures obtaining improvements over the baseline approach of 19.21%, 28.70%, and 8.27% respectively. We also demonstrate that our method is robust to the choice of hyperparameters.

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

Citation Download Citation

Caleb Parks, Susan Gauch, Matthew Scherreik, and Ryan Socha "Graph pretraining approach to utilize synthetic data for SAR ATR", Proc. SPIE 13032, Algorithms for Synthetic Aperture Radar Imagery XXXI, 130320X (7 June 2024); https://doi.org/10.1117/12.3025891

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
14 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Synthetic aperture radar

Feature extraction

Neural networks

Machine learning

Automatic target recognition

Image classification

RELATED CONTENT

Hybrid feature extraction based on PCA and CNN for oil...
Proceedings of SPIE (October 28 2022)

Utilizing contrastive learning for graph based active learning of SAR...
Proceedings of SPIE (June 13 2023)

Uncertainty-informed SAR image classification with Bayesian neural networks
Proceedings of SPIE (June 07 2024)

Modern approaches in deep learning for SAR ATR
Proceedings of SPIE (May 14 2016)

SAR target recognition and posture estimation using spatial pyramid pooling...
Proceedings of SPIE (January 12 2018)

Robustness of automatic target recognition using noniterative neural network
Proceedings of SPIE (May 19 2005)

Detection and classification of MSTAR objects via morphological shared weight...
Proceedings of SPIE (September 15 1998)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years