# SAMBA: A Scatter-Guided Masked Bidirectional Mamba Foundation Model for SAR Target Recognition

arXiv: https://arxiv.org/abs/2606.31668 · HTML: https://mlsanity.com/paper/2606.31668/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 24 of its 88 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [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)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [Gliding vertex on the horizontal bounding box for multi-oriented object detection](https://mlsanity.com/paper/1911.09358/) (2019)
- [Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing](https://mlsanity.com/paper/2310.18653/) (2023)
- [SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection](https://mlsanity.com/paper/2403.06534/) (2024)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks](https://mlsanity.com/paper/2007.02075/) (2020)
- [SARATR-X: Toward Building A Foundation Model for SAR Target Recognition](https://mlsanity.com/paper/2405.09365/) (2024)
- [SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification](https://mlsanity.com/paper/2311.04442/) (2023)
- [HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling](https://mlsanity.com/paper/2205.14949/) (2022)
- [DiffDet4SAR: Diffusion-based Aircraft Target Detection Network for SAR Images](https://mlsanity.com/paper/2404.03595/) (2024)
- [MaDiNet: Mamba Diffusion Network for SAR Target Detection](https://mlsanity.com/paper/2411.07500/) (2024)
- [What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs](https://mlsanity.com/paper/1906.01379/) (2019)
- [Global in Local: A Convolutional Transformer for SAR ATR FSL](https://mlsanity.com/paper/2308.05464/) (2023)
- [Crucial Feature Capture and Discrimination for Limited Training Data SAR ATR](https://mlsanity.com/paper/2308.10911/) (2023)
- [SAR-W-MixMAE: SAR Foundation Model Training Using Backscatter Power Weighting](https://mlsanity.com/paper/2503.01181/) (2025)

## Built on by (most cited first, 1 of 1)

- [SARATR-X-v2: Scale-Aware Structural Pre-Training for SAR Foundation Models](https://mlsanity.com/paper/2607.23238/) (2026)

## Abstract (arXiv)

Synthetic aperture radar automatic target recognition (SAR ATR) is critical for Earth observation and defense, but its practical deployment is constrained by scarce annotated training data. Self-supervised pre-training alleviates this label bottleneck, yet prevailing Transformer architectures incur prohibitive quadratic computational complexity, and conventional universal masking neglects the unique electromagnetic scattering properties intrinsic to SAR imagery. To address these limitations, we propose SAMBA (Scattering-Guided Bidirectional Mamba), an efficient self-supervised pre-training foundation model for SAR target interpretation. Our framework features three core innovations: (i) a linear-complexity Mamba encoder with a mid-sequence class token to mitigate computational bottlenecks; (ii) a three-level hierarchical Scattering-Guided Masked Autoencoder (SG-MAE) masking strategy guided by SAR physical priors, aligning the pretext task with SAR's intrinsic imaging mechanism; (iii) a lightweight SpatialMix feature interaction module to enhance cross-region feature fusion. We also design a two-stage cross-domain pre-training pipeline to optimize the overall pre-training process. Extensive evaluations demonstrate that SAMBA consistently delivers superior performance across all pre-training configurations, with substantially fewer parameters than both CNN and Transformer baselines. Compared with the default masking strategy in standard MAE, the proposed SG-MAE strategy further boosts the model's few-shot transfer capability. Benchmarking on seven downstream datasets covering classification and detection tasks shows SAMBA achieves state-of-the-art (SOTA) performance on most metrics, fully validating its robust generalizability across diverse SAR interpretation tasks. Source code and pre-trained weights are publicly available at https://github.com/mynswkk/SAMBA.