Paper 14031-10
Paper 14031-10
CLUTR: contextual learning for unambiguous target recognition
28 April 2026 • 11:00 AM - 11:20 AM EDT | National Harbor 5
Abstract
Target detection (TD) using Radar Range-Doppler Maps (RDMs) is a longstanding and critical challenge within the defense sector. Classical target detection approaches can struggle in cluttered environments. With the recent advancements of Vision-Language Models (VLMs), we explore an out-of-domain application of VLMs for target detection that leverages contextual information from human operators in the field. To enable this, we developed a scalable synthetic data generation pipeline for training and evaluation across two tasks: pointing and counting. We illustrate its effectiveness through numerical experiments by comparing an off-the-shelf VLM with a fine-tuned version. Our results show promise of this approach for enhancing radar-based target detection.
Presenter
Marie Chau
Johns Hopkins Univ. Applied Physics Lab., LLC (United States)
Marie has a Ph.D. in Applied Mathematics from the University of Maryland, College Park (UMCP) and undergraduate degrees in Mathematics, Economics, and Finance from UMCP. Before joining Johns Hopkins Applied Physics Laboratory as a Senior Machine Learning Researcher, Marie was an Assistant Professor of Operations Research at Virginia Commonwealth University. Her research interests and expertise include simulation optimization, broad areas of operations research and artificial intelligence, machine and statistical learning, and uncertainty quantification. Marie’s work has appeared in Winter Simulation Conference (WSC), IFAC/IEEE Workshop on Discrete Event Simulation, and AAAI Safe AI. She has also written a book chapter in the Handbook on Simulation Optimization.