SAFE: a SAR Feature Extractor based on self-supervised learning and masked Siamese ViTs
This addresses the problem of limited labeled data for SAR imagery, which is crucial for applications like disaster management and earth monitoring, by providing a versatile feature extractor, though it is incremental as it builds on existing self-supervised and transformer methods.
The paper tackles the scarcity of labeled Synthetic Aperture Radar (SAR) data by proposing SAFE, a self-supervised learning framework based on masked Siamese Vision Transformers, which creates a general feature extractor that competes with or surpasses state-of-the-art methods in few-shot classification and segmentation tasks without training on the evaluation sensors.
Due to its all-weather and day-and-night capabilities, Synthetic Aperture Radar imagery is essential for various applications such as disaster management, earth monitoring, change detection and target recognition. However, the scarcity of labeled SAR data limits the performance of most deep learning algorithms. To address this issue, we propose a novel self-supervised learning framework based on masked Siamese Vision Transformers to create a General SAR Feature Extractor coined SAFE. Our method leverages contrastive learning principles to train a model on unlabeled SAR data, extracting robust and generalizable features. SAFE is applicable across multiple SAR acquisition modes and resolutions. We introduce tailored data augmentation techniques specific to SAR imagery, such as sub-aperture decomposition and despeckling. Comprehensive evaluations on various downstream tasks, including few-shot classification, segmentation, visualization, and pattern detection, demonstrate the effectiveness and versatility of the proposed approach. Our network competes with or surpasses other state-of-the-art methods in few-shot classification and segmentation tasks, even without being trained on the sensors used for the evaluation.