SAR ATR

ATR: Automatic Target Recognition · SAR: Synthetic Aperture Radar

Ask about this topic

Latest papers

CardsList

13 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Sep 17, 2026

LoRA Enhanced Contrastive Learning with SAS Vision Transformers

Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, background clutter, and human-in-the-loop assessment. We adapt DINOv3 Vision Transformer (ViT) models to underwater SAS ATR using a three-stage parameter-efficient framework. Stage 1 uses Low-Rank Adaptation (LoRA) while freezing the ViT backbone, bridging the gap between natural-image pretraining and underwater acoustic propagation. Stage 2 uses hard-negative mining to strengthen the decision boundary against acoustic mimics, including rocks and sediment formations resembling man-made targets. Stage 3 uses Supervised Contrastive Learning (SupCon) to separate target and clutter representations. We evaluate at-sea SAS data using a mission-level geographic split, compare all arms at 85 percent test recall, and repeat each comparison over three random seeds. LoRA accounts for the primary effect, increasing area under the precision-recall curve (AUPRC) from 0.300 to 0.679 +/- 0.027 using the same frozen backbone. Rank 4 achieves this result while training only 0.26 percent of weights. Neither refinement stage exceeds its matched control: hard-negative mining changes AUPRC by -0.0045 +/- 0.0119 versus an equal-size random curriculum, and SupCon changes AUPRC by +0.0002 +/- 0.0096 versus the preceding stage. These null results indicate that mining occurred on data the encoder had already fit and that supervised stages had already imposed most target-clutter geometry. One efficient adaptation stage is sufficient; stacked refinement is not.

Dan Zimmerman, Frank E. Bobe, Amelia L. McCormack +2

Center for Connected Autonomy & AI Florida Atlantic University Boca Raton, USA · Naval Surface Warfare Center Panama City Division Panama City, USA · Department of Computer Science Florida State University Tallahassee, USA

SAR ATRUnderwater Object DetectionUnderwater ImagingLow-Rank AdaptationUnderwater Acoustics
AskPDF
Sep 7, 2026

Cross-modal learning for SAR target recognition using optical vision foundation models

Synthetic Aperture Radar (SAR) is an important modality in a wide range of imaging applications due to its versatile, long range and near all weather operating capabilities. However, Automatic Target Recognition (ATR) remains a challenging problem due to limited labelled data, the strong speckle in SAR images and the significant domain gap between SAR and more abundant optical imagery. In contrast, electro-optical (EO) imagery benefits from massive datasets, clearer visual structure and powerful foundation models. In this work, we investigate how vision foundation models trained on optical data can provide class level supervision for SAR classification. We propose a cross-modal EO to SAR prototype alignment framework in which a frozen EO encoder, based on a DINOv3 vision foundation model, is used to construct class level optical prototypes without requiring strict EO/SAR pairs. A SAR model is then trained to classify SAR images while aligning its embeddings to the corresponding EO class prototype. At inference time, the SAR model operates independently, without access to optical imagery. We evaluate our approach on the UNICORNv2 dataset, an EO and SAR dataset of civilian vehicles with heavily speckled images and severe class imbalance. EO prototype alignment improves SAR classification accuracy over frozen DINOv3, SAR only finetuning and unpaired distribution alignment baselines, and t-SNE visualizations provide qualitative evidence of clearer separation among classes in the trained SAR embedding space. These results suggest that optical vision foundation models, despite being trained on visible spectrum imagery, provide transferable information for SAR image classification, offering a practical method for using large scale pretrained vision foundation models across challenging sensing modalities.

Lucas Hirsch, James R. Hopgood, Javid Khan +2

School of Engineering, University of Edinburgh, United Kingdom · Leonardo UK, United Kingdom · School of Engineering and Physical Sciences, Heriot-Watt University, United Kingdom

Cross-Modal AlignmentCross-Modal Representation TransferTransfer LearningSynthetic Aperture RadarSAR ATR
AskPDF
Jul 21, 2026

Fast Generation of Representative Synthetic Dataset with Salsa to Train ATR Models with Electromagnetic Couplings Data-Augmentation

This work focuses on training Automatic Target Recognition (ATR) models using simulated Synthetic Aperture Radar (SAR) images to circumvent the lack of real measurements. To obtain robust and versatile ATR models, simulation needs to generate massive datasets that encompass all the variability found in real measurements. Thus, we need a simulator that finds a good tradeoff between execution speed, computational resource consumption, and physical representativeness. In this work, we demonstrate that the Salsa simulator addresses this issue. We ran computing performance tests to show that Salsa can generate 21,600 synthetic images in less than 10 minutes using a single Nvidia GeForce RTX 4090 GPU. Using our ADASCA Deep Learning approach, we demonstrate that these data are sufficiently representative to train ATR models and reach state-of-the-art results on the MSTAR public dataset with an accuracy of 86 %. To illustrate how Salsa unlocks new possibilities to train ATR models, we use the simulator to conduct a study on Electromagnetic (EM) couplings between the targets and their immediate environment. We demonstrate that, if not accounted for in the training dataset, the variability of the EM couplings induced by the variability of the ground surfaces can significantly degrade the performance of ATR models, with an accuracy decrease of more than 4 %. We also show that Salsa can generate in a timely manner (i.e., in less than 4 hours using the same GPU as previously) a massive dataset of 648,000 images with a large variety of couplings to make the ATR models robust to EM coupling variations. Our ATR models can then achieve an accuracy of 87 % on the MSTAR dataset.

Benjamin Camus, Julien Houssay, Corentin Le Barbu +3

DGA.MI · Scalian DS 2 rue Antoine Becquerel 35700 Rennes, France · DGA Maîtrise de l’Information BP 7 35998 Rennes CEDEX 9, France

Synthetic Data GenerationSynthetic Aperture RadarSAR ATR
AskPDF
Jul 8, 2026

A Generalized Deep Non-negative Matrix Factorization Approach for SAR Automatic Target Recognition

The deep nonnegative matrix factorization (DNMF) technique is proposed to address the low interpretability of deep learning-based methods in extracting multilayer features from synthetic aperture radar (SAR) target samples. However, existing DNMF methods employ a layer-by-layer decomposition strategy, which is prone to causing error accumulation and local optimum, thereby hindering a consistent improvement in recognition accuracy as the number of layer increases. In this paper, a robust multilayer feature extraction method, termed generalized deep non-negative matrix factorization (G-DNMF), is proposed to address the above challenges in SAR automatic target recognition (ATR). The G-DNMF aims global optimality and derives the update rules for each parameter using lagrangian multiplier method. The new update formula indicates that both the DNMF method based on the encoding matrix and the mixing matrix are special cases of the proposed method, theoretically demonstrating the universality of proposed method. In general, the proposed method discards the layer-by-layer decomposition strategy, thereby effectively mitigating the risk of local optima and eliminating error accumulation, leading to a significant improvement in DNMF's multi-layer feature extraction capability. The experimental results, by presenting the feature images extracted from each layer by G-DNMF and the reconstructed original images, verified the proposed method's pure additive understanding of multi-layer features and demonstrated its interpretability. The experimental results based on MSTAR and OpenSARship datasets show that G-DNMF outperforms existing DNMF algorithms and their derivatives in terms of stability and recognition performance.

Yunhong Zhang, Changjie Cao, Zhongli Zhou +4

Non-Negative Matrix FactorizationRemote SensingSynthetic Aperture RadarSAR ATR
AskPDF
Jun 30, 2026

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

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.

Ke Wang, Xiaoyi Pan, Zhaoyu Gu +4

College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China

MambaSelf-Supervised Pre-TrainingRemote SensingSynthetic Aperture RadarSAR ATRMasked Image Modeling
AskPDF
Jun 3, 2026

Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning

Few-shot class-incremental learning (FSCIL) in synthetic aperture radar imagery presents unique challenges due to severe data scarcity and SAR-specific variability. In particular, strong azimuth sensitivity in SAR induces large intra-class variation and inter-class confusion, and FSCIL sequential updates further lead to catastrophic forgetting of previously learned classes. Inspired by neural collapse, we propose an optical-guided SAR FSCIL framework, which derives orthogonal feature subspaces from a data-rich optical ATR dataset and uses them as geometric priors to guide SAR feature learning. SAR features are projected onto these orthogonal subspaces via principal angle constraints, effectively transferring discriminative structure from the optical to the SAR domain. Specifically, our projection loss and the classifier loss optimized with a frozen simplex-ETF geometry jointly induce neural collapse by concentrating features around class means while maintaining large inter-class angles. We evaluate the approach on a benchmark comprising an optical ATR dataset and a SAR ATR dataset with 24 target classes, organized into a base training session and seven incremental sessions. Compared with recent FSCIL methods including NCFSCIL and so on, our method achieves the highest final accuracy and a favorable trade-off between final performance and performance degradation. Moreover, neural collapse metrics show improved intra-class compactness and inter-class separability, indicating that the learned features more closely approximate the ideal simplex-ETF geometry.

Fan Zhang, Sijin Zheng, Fei Ma +4

School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China · School of Information Science and Technology and the Interdisciplinary Research Center for Artificial Intelligence, Beijing University of Chemical Technology, Beijing 100029, China · Beihang University, Beijing 100191, China +1

Class-Incremental LearningRemote SensingIncremental LearningSynthetic Aperture RadarSAR ATRFew-Shot Image Classification+1
AskPDF
May 15, 2026

Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification

Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critical applications such as synthetic aperture radar (SAR) automatic target recognition (ATR). Randomized smoothing improves robustness by averaging predictions over noisy inputs, but isotropic noise often fails to preserve the semantic structure of SAR imagery. We propose semantic smoothing, a defense that replaces noised-based perturbations with structured randomized transformations generated by a novel view synthesis model. For SAR, we condition on acquisition geometry to synthesize multiple plausible radar views. Predictions across generated randomized views are aggregated to form a robust classifier. Experiments show that semantic smoothing improves robustness against standard attacks, such as FGSM and PGD, and SAR-specific attacks, such as OTSA and SMGAA, while also increasing clean classification accuracy. These results demonstrate that randomized smoothing via semantically preserving geometric transformations is a promising alternative to isotropic noise for adversarial defense in structured sensing domains.

Daniel Brignac, Fengwei Tian, Banafsheh Latibari +2

The University of Arizona Tucson, Arizona, United States

Adversarial RobustnessAdversarial AttacksNeural Network RobustnessRandomized SmoothingSynthetic Aperture RadarImage Classification+1
AskPDF
May 11, 2026

Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition

Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The merging of these data domains represents a significant paradigm shift with far-reaching implications for automatic target recognition (ATR). Recent transformer-based LLVM research has shown substantial improvements for geospatial perception tasks. Our study examines the application of LLVM to remote sensing image captioning and visual question-answering (VQA), with a specific focus on synthetic aperture radar (SAR) imagery. We examine newly published LLVM methods, including CLIP and LLaVA neural network transformer architectures. We have developed a work-in-progress SAR training and evaluation benchmark derived from the MSTAR Public Dataset. This has been extended to include descriptive text captions and question-answer pairs for VQA tasks. This challenge dataset is designed to push the boundaries of an LLVM in identifying nuanced ATR details in SAR imagery. Utilizing parameter-efficient fine-tuning, we train an LLVM method to identify fine-grained target qualities at 98% accuracy. We detail our data setup and experiments, addressing potential pitfalls that could lead to misleading conclusions. Accurately identifying and differentiating military vehicle types in SAR data poses a critical challenge, especially under complex environmental conditions. Mastering this target recognition skill may require a human analyst months of training and years of practice. This research represents a unique effort to apply LLVM to SAR applications, advancing machine-assisted remote sensing ATR for military and intelligence contexts.

David F. Ramirez, Tim L. Overman, Kristen Jaskie +2

SenSIP Center, School of ECEE, Arizona State University, Tempe, Arizona · Prime Solutions Group, Goodyear, Arizona

Remote Sensing Image UnderstandingRemote Sensing VQALarge Vision-Language ModelsRemote SensingSAR ATR
AskPDF
Apr 21, 2026

Online CS-based SAR Edge-Mapping

With modern defense applications increasingly relying on inexpensive, small Unmanned Aerial Vehicles (UAVs), a major challenge lies in designing intelligent and computationally efficient onboard Automatic Target Recognition (ATR) algorithms to carry out operational objectives. This is especially critical in Synthetic Aperture Radar (SAR), where processing techniques such as ATR are often carried out post data collection, requiring onboard systems to bear the memory burden of storing the back-scattered signals. To alleviate this high cost, we propose an online, direct, edge-mapping technique which bypasses the image reconstruction step to classify scenes and targets. Furthermore, by reconstructing the scene as an edge-map we inherently promote sparsity, requiring fewer measurements and computational power than classic SAR reconstruction algorithms such as backprojection.

Conor Flynn, Radoslav Ivanov, Birsen Yazici

Rensselaer Polytechnic Institute, Troy, New York, USA

Edge DetectionRemote SensingCompressed SensingSynthetic Aperture RadarUAV Remote SensingSAR ATR
AskPDF
Apr 14, 2026

Magnitude Is All You Need? Rethinking Phase in Quantum Encoding of Complex SAR Data

Synthetic Aperture Radar (SAR) data is inherently complex-valued, while quantum machine learning (QML) models operate in complex Hilbert spaces. This similarity suggests that using both the magnitude and phase of SAR data in quantum encoding should help automatic target recognition in SAR images. In this study, we test this assumption by comparing five encoding strategies for quantum models: magnitude-only encoding, joint magnitude-phase encoding, in-phase and quadrature encoding, preprocessed phase encoding, and a purely quantum architecture. All approaches are evaluated under a unified experimental setup on the MSTAR benchmark dataset. Surprisingly, we find that magnitude-only encoding performs better than phase-inclusive encodings in hybrid quantum-classical models. It achieves 99.57 percent accuracy on the 3-class task and 71.19 percent accuracy on the 8-class task, outperforming complex-valued alternatives under the same framework. Adding phase information provides little or no improvement and can sometimes degrade performance. However, in purely quantum models with only 184 to 224 trainable parameters and no classical neural-network layers, phase information becomes much more important, improving accuracy by up to 21.65 percentage points. These findings show that the usefulness of phase information depends not only on the data, but also on the architecture used to process it. Hybrid models can compensate for missing phase information through their classical components, while pure quantum models rely more strongly on phase information for class discrimination. The results provide practical guidance for encoding complex-valued data in quantum machine learning and highlight the importance of jointly designing encoding strategies and model architectures for current quantum systems.

Sakthi Prabhu Gunasekar, Prasanna Kumar Rangarajan

Dept. of Computer Science & Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, India

SAR ATRQuantum Data EncodingQuantum Machine LearningQuantum Neural NetworksHybrid Quantum-Classical ML
AskPDF
Mar 23, 2026

FSCE: A Target-Aware Frequency-Spatial Collaborative Enhancement Framework for Noise-Resilient SAR ATR

Synthetic aperture radar automatic target recognition (SAR ATR) is severely challenged by coherent speckle noise, whose interference can be progressively amplified by hierarchical nonlinear transformations and eventually damage high-level semantic representations. To address this issue, we propose a Target-Aware Frequency-Spatial Collaborative Enhancement (FSCE) framework for noise-resilient SAR ATR, which integrates frequency-spatial modeling for early feature stabilization with semantic regularization. Specifically, we design a Frequency-Spatial Early-stage Adaptive Enhancement (FS-EAE) module at the network entrance to suppress noise propagation and preserve target structures through collaborative spatial-frequency modeling. Building upon stabilized shallow representation, we further introduce an Adaptive Policy-driven Semantic Alignment (APSA) mechanism, which uses an online teacher policy to impose top-down semantic constraints on the student and feeds semantic guidance back to the enhanced early features during training. Experiments on MSTAR, OpenSARShip, and FUSARShip demonstrate the effectiveness of this synergy. Moreover, the competitive performance of our lightweight impletation FSCE-Netμ\text{FSCE-Net}_μ with only 0.17M parameters suggests that the proposed framework is applicable to both high-capacity and lightweight architectures.

Yansong Lin, Zihan Cheng, Ziyue Yang +4

Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, China · School of Computer Science and Engineering (School of Artificial Intelligence), Wuhan Institute of Technology, China · Institute of Automation, Chinese Academy of Sciences, China +1

Image Corruption RobustnessFrequency-Domain Feature LearningRemote SensingSynthetic Aperture RadarSAR ATR
AskPDF
Feb 27, 2026

RSTNet: Enhancing Small-Target Recognition in Noisy SAR Imagery via Robust Feature Learning and Distribution-Aware Regression

SAR supports all-day-and-night oceanic observation, yet vessel identification from SAR images is hampered by speckle noise, intricate land-sea backgrounds and dim miniature vessels, yielding numerous false identifications and missed targets. We develop an SAR-adaptive stable detection model RSTNet based on YOLOv8. A large-kernel channel-separated denoising unit eliminates noise and reserves delicate vessel features; parallel patch-aware attention enhances multi-scale feature extraction for miniature objects; NWD loss substitutes conventional IoU loss to achieve accurate bounding box regression. The proposed model outperforms the original YOLOv8 on the SSDD dataset with 97.0% precision, 95.1% recall and 98.9% [email protected]. Validations on the HRSID dataset verify its favorable generalization capacity for coastal miniature vessels. Therefore, our work delivers an effective technical scheme for ocean observation imaging with noisy miniature targets. The source code is available at https://github.com/renhcmhx/SAR.git.

Xiaojing Zhao, Shiyang Li, Zenan Chu +5

College of Mathematics and Information Science, Anyang Institute of Technology, Anyang, 455000, China · School of Computer Science and Information Engineering, Anyang Institute of Technology, Anyang, 455000, China · College of Electronic Information and Optical Engineering, Nankai University, Tianjin, 300350, China +3

Synthetic Aperture RadarSmall Object DetectionRemote SensingRemote Sensing Small Object DetectionObject DetectionShip Detection+1
AskPDF
Dec 31, 2025

Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognition

As a critical application of computational intelligence in remote sensing, deep learning-based synthetic aperture radar (SAR) image target recognition facilitates intelligent perception but typically relies on centralized training, where multi-source SAR data are uploaded to a single server, raising privacy and security concerns. Federated learning (FL) provides an emerging computational intelligence paradigm for SAR image target recognition, enabling cross-site collaboration while preserving local data privacy. However, FL confronts critical security risks, where malicious clients can exploit SAR's multiplicative speckle noise to conceal backdoor triggers, severely challenging the robustness of the computational intelligence model. To address this challenge, we propose NADAFD, a noise-aware and dynamically adaptive federated defense framework that integrates frequency-domain, spatial-domain, and client-behavior analyses to counter SAR-specific backdoor threats. Specifically, we introduce a frequency-domain collaborative inversion mechanism to expose cross-client spectral inconsistencies indicative of hidden backdoor triggers. We further design a noise-aware adversarial training strategy that embeds ΓΓ-distributed speckle characteristics into mask-guided adversarial sample generation to enhance robustness against both backdoor attacks and SAR speckle noise. In addition, we present a dynamic health assessment module that tracks client update behaviors across training rounds and adaptively adjusts aggregation weights to mitigate evolving malicious contributions. Experiments on MSTAR and OpenSARShip datasets demonstrate that NADAFD achieves higher accuracy on clean test samples and a lower backdoor attack success rate on triggered inputs than existing federated backdoor defenses for SAR target recognition.

Yuchao Hou, Zixuan Zhang, Jie Wang +9

Shanxi Normal University, Taiyuan, China · Guizhou University, Guiyang, China · Shanxi Key Laboratory of Cryptography and Data Security, School of Computer Science and Artificial Intelligence, Shanxi Normal University, Taiyuan 030031, China +15

Adversarial TrainingRemote SensingSynthetic Aperture RadarSAR ATRFederated Learning
AskPDF