SARATR-X: Towards Building A Foundation Model for SAR Target Recognition

2024-05-15

AI Summary

Existing SAR ATR methods rely heavily on large-scale labeled datasets and exhibit poor generalization, hindering real-world deployment. To address these limitations, we propose SARATR-X—the first foundation model for SAR target recognition—breaking away from conventional supervised learning and closed-set paradigms. Our approach features: (1) a SAR-customized hybrid backbone integrating Transformer and CNN architectures; (2) a two-stage self-supervised learning framework driven by multi-scale gradient features, trained on 180,000 unlabeled SAR images to learn robust, generalizable representations; and (3) SAR-ATR-Bench, the largest publicly available SAR target benchmark dataset to date. Extensive experiments demonstrate that SARATR-X achieves performance on par with or superior to fully supervised and semi-supervised methods in few-shot classification and cross-scene detection, while significantly reducing annotation costs and enhancing model robustness and generalization. The code and dataset are publicly released.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Semi-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on detecting and classifying a specific category, e.g., vehicles, ships, airplanes, or buildings. One of the fundamental limitations of the top-performing SAR ATR methods is that the learning paradigm is supervised, task-specific, limited-category, closed-world learning, which depends on massive amounts of accurately annotated samples that are expensively labeled by expert SAR analysts and have limited generalization capability and scalability. In this work, we make the first attempt towards building a foundation model for SAR ATR, termed SARATR-X. SARATR-X learns generalizable representations via self-supervised learning (SSL) and provides a cornerstone for label-efficient model adaptation to generic SAR target detection and classification tasks. Specifically, SARATR-X is trained on 0.18 M unlabelled SAR target samples, which are curated by combining contemporary benchmarks and constitute the largest publicly available dataset till now. Considering the characteristics of SAR images, a backbone tailored for SAR ATR is carefully designed, and a two-step SSL method endowed with multi-scale gradient features was applied to ensure the feature diversity and model scalability of SARATR-X. The capabilities of SARATR-X are evaluated on classification under few-shot and robustness settings and detection across various categories and scenes, and impressive performance is achieved, often competitive with or even superior to prior fully supervised, semi-supervised, or self-supervised algorithms. Our SARATR-X and the curated dataset are released at https://github.com/waterdisappear/SARATR-X to foster research into foundation models for SAR image interpretation.

Problem

• SAR ATR
• target recognition
• data demand and generalization

Innovation

• Self-learning SAR ATR
• Unsupervised Learning
• Large Unlabeled SAR Dataset