Semi-supervised domain transfer for robust maritime satellite image classification

You are here: Homepage > Search

Semi-supervised domain transfer for robust maritime satellite image classification

Emmanuel, Patrick R. / Ratto, Christopher R. / Drenkow, Nathan G. / Markowitz, Jared J.

Naval intelligence plays a critical role in multi-domain operations by identifying and tracking vessels of interest, especially suspected “dark ships” operating in an emissions-controlled (EMCON) state. While applying machine learning (ML) to maritime satellite imagery could enable an automated open-ocean search capability for dark ships, ensuring the robustness of ML models to environmental variations in the maritime domain remains a challenge because training sets do not encapsulate all possible environmental conditions. To address the challenge of unsupervised domain adaptation (UDA) in ship classification, i.e. transferring a ML model from a labeled source domain to an unlabeled target domain, we propose employing combinations of semi-supervised learning (SSL) techniques with standalone UDA approaches. Specifically, we incorporate combinations of FixMatch, minimum class confusion, gradient reversal, and mixup augmentation into the standard cross-entropy supervised loss function. These interventions were compared in two domain shift settings, one in which the source and target domains are both comprised of simulated data, and another in which the source domain consists of only simulated data, and the target domain consists of only real data. Experimental results comparing the combinations of interventions to a regularized fine-tuning baseline demonstrate that the greatest improvements in model robustness were achieved when combinations of our SSL strategy (FixMatch) and UDA algorithms were incorporated into training.

Access

Check access

Check availability in my library

Order at Subito €

Export, share and cite

Document information

Title :

Semi-supervised domain transfer for robust maritime satellite image classification

Contributors:

Solomon, Latasha (editor) / Schwartz, Peter J. (editor) / Emmanuel, Patrick R. (author) / Ratto, Christopher R. (author) / Drenkow, Nathan G. (author) / Markowitz, Jared J. (author)

Conference:

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V ; 2023 ; Orlando, Florida, United States

Published in:

Proc. SPIE ; 12538

Publication date :

2023-06-12

ISBN :

9781510661929

ISSN :

0277-786X

DOI :

https://doi.org/10.1117/12.2661684