Mstar
PulseAugur coverage of Mstar — every cluster mentioning Mstar across labs, papers, and developer communities, ranked by signal.
-
New FSCE framework enhances SAR ATR noise resilience
Researchers have developed a new framework called FSCE (Frequency-Spatial Collaborative Enhancement) to improve the accuracy of Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) systems, particularly in th…
-
New framework defends federated learning against SAR image backdoor attacks
Researchers have developed NADAFD, a novel framework designed to defend against backdoor attacks in federated learning for Synthetic Aperture Radar (SAR) image target recognition. This framework integrates frequency-dom…
-
MSTAR framework enhances time series classification via neural architecture search
Researchers have developed MSTAR, a novel framework for Neural Architecture Search (NAS) specifically designed for Time Series Classification (TSC). This approach addresses limitations in previous methods by considering…
-
GeoDiff-SAR uses geometric priors to enhance SAR image generation
Researchers have developed GeoDiff-SAR, a novel diffusion model that uses geometric priors to improve the generation of synthetic aperture radar (SAR) images, particularly for scenarios with sparse observation angles. B…
-
New G-DNMF method enhances SAR target recognition accuracy
Researchers have introduced a new method called Generalized Deep Non-negative Matrix Factorization (G-DNMF) to improve synthetic aperture radar (SAR) automatic target recognition (ATR). This approach addresses limitatio…
-
LLVMs applied to SAR imagery for military target recognition
Researchers have developed a new benchmark and training methodology for applying large language-vision models (LLVMs) to automatic target recognition (ATR) using synthetic aperture radar (SAR) imagery. The study leverag…
-
Quantum ML research finds magnitude-only encoding outperforms phase in hybrid models
A new research paper explores the encoding of complex-valued Synthetic Aperture Radar (SAR) data in quantum machine learning models. The study found that magnitude-only encoding surprisingly outperformed phase-inclusive…