Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition

2026-05-11

AI Summary

This study addresses the challenge of fine-grained recognition of military vehicles in synthetic aperture radar (SAR) imagery under complex environments by introducing large language-vision models to the SAR automatic target recognition domain for the first time. Leveraging the MSTAR dataset, the authors construct the first vision-language benchmark tailored for military remote sensing, encompassing visual question answering (VQA) and image captioning tasks. Building upon Transformer-based architectures such as CLIP and LLaVA, the proposed approach employs parameter-efficient fine-tuning strategies during training. The method achieves a 98% accuracy rate on fine-grained target attribute recognition, substantially enhancing identification performance in complex scenarios and establishing a novel paradigm for machine-assisted intelligence analysis.

Abstract

Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The merging of these data domains represents a significant paradigm shift with far-reaching implications for automatic target recognition (ATR). Recent transformer-based LLVM research has shown substantial improvements for geospatial perception tasks. Our study examines the application of LLVM to remote sensing image captioning and visual question-answering (VQA), with a specific focus on synthetic aperture radar (SAR) imagery. We examine newly published LLVM methods, including CLIP and LLaVA neural network transformer architectures. We have developed a work-in-progress SAR training and evaluation benchmark derived from the MSTAR Public Dataset. This has been extended to include descriptive text captions and question-answer pairs for VQA tasks. This challenge dataset is designed to push the boundaries of an LLVM in identifying nuanced ATR details in SAR imagery. Utilizing parameter-efficient fine-tuning, we train an LLVM method to identify fine-grained target qualities at 98% accuracy. We detail our data setup and experiments, addressing potential pitfalls that could lead to misleading conclusions. Accurately identifying and differentiating military vehicle types in SAR data poses a critical challenge, especially under complex environmental conditions. Mastering this target recognition skill may require a human analyst months of training and years of practice. This research represents a unique effort to apply LLVM to SAR applications, advancing machine-assisted remote sensing ATR for military and intelligence contexts.

Problem

• Automatic Target Recognition
• Synthetic Aperture Radar
• Military Vehicle Classification
• Remote Sensing
• Visual Question Answering

Innovation

• Large Language-Vision Models
• Synthetic Aperture Radar
• Visual Question Answering
• Automatic Target Recognition
• Parameter-Efficient Fine-Tuning