SARATR-X: Toward Building a Foundation Model for SAR Target Recognition
Top Cited Papers
Open Access
- 28 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 869-884
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.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62376283)
- Science Fund for Distinguished Young Scholars of Hunan Province (2024JJ2066)
- science and technology innovation Program of Hunan Province (2022RC1092)
- Key Stone of the National University of Defense Technology (JS2023-03)
This publication has 102 references indexed in Scilit:
- LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model2024
- LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images2024
- Visual attention networkComputational Visual Media, 2023
- Crucial feature capture and discrimination for limited training data SAR ATRISPRS Journal of Photogrammetry and Remote Sensing, 2023
- A broad review on class imbalance learning techniquesApplied Soft Computing, 2023
- ObjectBox: From Centers to Boxes for Anchor-Free Object Detection2022
- Physically explainable CNN for SAR image classificationISPRS Journal of Photogrammetry and Remote Sensing, 2022
- SAR data applications in earth observation: An overviewExpert Systems with Applications, 2022
- FUSAR-Ship: building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognitionScience China Information Sciences, 2020
- Group Invariant ScatteringCommunications on Pure and Applied Mathematics, 2012