SARMAE: Masked Autoencoder for SAR Representation Learning
This work addresses data scarcity and noise issues in SAR remote sensing, enabling improved deep learning applications for all-weather monitoring, but it is incremental as it builds on existing masked autoencoder methods.
The paper tackles the challenges of data scarcity and speckle noise in Synthetic Aperture Radar (SAR) imagery by proposing SARMAE, a self-supervised masked autoencoder, which achieves state-of-the-art performance on classification, detection, and segmentation tasks across multiple datasets.
Synthetic Aperture Radar (SAR) imagery plays a critical role in all-weather, day-and-night remote sensing applications. However, existing SAR-oriented deep learning is constrained by data scarcity, while the physically grounded speckle noise in SAR imagery further hampers fine-grained semantic representation learning. To address these challenges, we propose SARMAE, a Noise-Aware Masked Autoencoder for self-supervised SAR representation learning. Specifically, we construct SAR-1M, the first million-scale SAR dataset, with additional paired optical images, to enable large-scale pre-training. Building upon this, we design Speckle-Aware Representation Enhancement (SARE), which injects SAR-specific speckle noise into masked autoencoders to facilitate noise-aware and robust representation learning. Furthermore, we introduce Semantic Anchor Representation Constraint (SARC), which leverages paired optical priors to align SAR features and ensure semantic consistency. Extensive experiments across multiple SAR datasets demonstrate that SARMAE achieves state-of-the-art performance on classification, detection, and segmentation tasks. Code and models will be available at https://github.com/MiliLab/SARMAE.