NUDT4MSTAR: A New Dataset and Benchmark Towards SAR Target Recognition in the Wild

2025-01-23

AI Summary

Wild-scenario SAR vehicle recognition is hindered by the scarcity of high-quality, large-scale benchmark datasets. Method: This paper introduces NUDT4MSTAR—the first large-scale, multimodal, field-deployable SAR target recognition benchmark—featuring 40 vehicle classes, 5 realistic operational scenarios, and over 190,000 amplitude and complex-valued SAR images, all accompanied by precise imaging parameters and target-level annotations. It establishes a novel open-data paradigm integrating multi-scene, multi-condition, and full-format (complex + amplitude) SAR imagery. Contribution/Results: NUDT4MSTAR constitutes the first fine-grained, field-oriented SAR recognition benchmark. We systematically evaluate 15 representative algorithms across seven core tasks—including cross-domain transfer—and demonstrate that transfer learning from NUDT4MSTAR significantly improves performance on three downstream datasets (e.g., MSTAR) by up to 12.7% in accuracy. With data volume tenfold larger than prior benchmarks, NUDT4MSTAR is publicly released to advance the SAR automatic target recognition community.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Security and Privacy: Large-scale security measurements

Abstract

Synthetic Aperture Radar (SAR) stands as an indispensable sensor for Earth observation, owing to its unique capability for all-day imaging. Nevertheless, in a data-driven era, the scarcity of large-scale datasets poses a significant bottleneck to advancing SAR automatic target recognition (ATR) technology. This paper introduces NUDT4MSTAR, a large-scale SAR dataset for vehicle target recognition in the wild, including 40 target types and a wide array of imaging conditions across 5 different scenes. NUDT4MSTAR represents a significant leap forward in dataset scale, containing over 190,000 images-tenfold the size of its predecessors. To enhance the utility of this dataset, we meticulously annotate each image with detailed target information and imaging conditions. We also provide data in both processed magnitude images and original complex formats. Then, we construct a comprehensive benchmark consisting of 7 experiments with 15 recognition methods focusing on the stable and effective ATR issues. Besides, we conduct transfer learning experiments utilizing various models trained on NUDT4MSTAR and applied to three other target datasets, thereby demonstrating its substantial potential to the broader field of ground objects ATR. Finally, we discuss this dataset's application value and ATR's significant challenges. To the best of our knowledge, this work marks the first-ever endeavor to create a large-scale dataset benchmark for fine-grained SAR recognition in the wild, featuring an extensive collection of exhaustively annotated vehicle images. We expect that the open source of NUDT4MSTAR will facilitate the development of SAR ATR and attract a wider community of researchers.

Problem

• Synthetic Aperture Radar (SAR) Imagery
• Data Scarcity
• Automatic Target Recognition

Innovation

• NUDT4MSTAR Dataset
• SAR Radar Imagery
• Vehicle Recognition