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

arXiv: https://arxiv.org/abs/2405.09365 · HTML: https://mlsanity.com/paper/2405.09365/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 132 references that are in the map.
- First posted on arXiv 15 May 2024.

## Builds on (most cited first, 30 of 59)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Sequential Modeling Enables Scalable Learning for Large Vision Models](https://mlsanity.com/paper/2312.00785/) (2023)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images](https://mlsanity.com/paper/2403.11703/) (2024)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)
- [Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model](https://mlsanity.com/paper/2208.03987/) (2022)

## Built on by (most cited first, 25 of 25)

- [ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild](https://mlsanity.com/paper/2501.13354/) (2025)
- [Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodality](https://mlsanity.com/paper/2603.00988/) (2026)
- [M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision](https://mlsanity.com/paper/2507.16318/) (2025)
- [SARMAE: Masked Autoencoder for SAR Representation Learning](https://mlsanity.com/paper/2512.16635/) (2025)
- [Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation](https://mlsanity.com/paper/2504.06962/) (2025)
- [OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation](https://mlsanity.com/paper/2509.15096/) (2025)
- [X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images](https://mlsanity.com/paper/2407.19436/) (2024)
- [On the Status of Foundation Models for SAR Imagery](https://mlsanity.com/paper/2509.21722/) (2025)
- [FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing](https://mlsanity.com/paper/2509.23927/) (2025)
- [RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains](https://mlsanity.com/paper/2511.02331/) (2025)
- [HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation](https://mlsanity.com/paper/2604.11444/) (2026)
- [Multi-Expert Learning Framework with the State Space Model for Optical and SAR Image Registration](https://mlsanity.com/paper/2507.04397/) (2025)
- [SAR-RAG: ATR Visual Question Answering by Semantic Search, Retrieval, and MLLM Generation](https://mlsanity.com/paper/2602.04712/) (2026)
- [Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition](https://mlsanity.com/paper/2604.01903/) (2026)
- [Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder](https://mlsanity.com/paper/2604.16952/) (2026)
- [SAMBA: A Scatter-Guided Masked Bidirectional Mamba Foundation Model for SAR Target Recognition](https://mlsanity.com/paper/2606.31668/) (2026)
- [Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method](https://mlsanity.com/paper/2607.09078/) (2026)
- [Deep Learning-based Cross-modal Reconstruction of Vehicle Target from Sparse 3D SAR Image](https://mlsanity.com/paper/2406.04158/) (2024)
- [Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognition](https://mlsanity.com/paper/2601.00900/) (2025)
- [Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition](https://mlsanity.com/paper/2605.10772/) (2026)
- [Physics-Driven Semantic Scattering Structure Understanding of Aircraft Target in SAR Images](https://mlsanity.com/paper/2606.06847/) (2026)
- [CMTFormer: Marrying Transformer with Hierarchical Information Interaction for RGB-Event Object Detection](https://mlsanity.com/paper/2606.29136/) (2026)
- [Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?](https://mlsanity.com/paper/2607.20284/) (2026)
- [ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution](https://mlsanity.com/paper/2609.02377/) (2026)
- [Cross-modal learning for SAR target recognition using optical vision foundation models](https://mlsanity.com/paper/2609.07753/) (2026)

## Abstract (arXiv)

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.