SARATR-X-v2: Scale-aware structural pretraining for synthetic aperture radar foundation models

Masked image modeling (MIM) has become a dominant paradigm for synthetic aperture radar (SAR) pretraining, yet the design of the reconstruction target remains fundamentally unsettled. This article argues that a SAR pretraining target should satisfy two conditions to produce transferable representations: 1) physics-grounded stability, i.e., approximate invariance of the target operator to multiplicative speckle inherent in coherent imaging, and 2) semantic scale compatibility, i.e., coverage of the heterogeneous spatial scales that downstream tasks demand. These two conditions are individually achievable but jointly difficult: physics-grounded stability favors fixed operators, while semantic scale compatibility favors data-driven composition. To this end, SARATR-X-v2 reconciles both within a single design. The target is constructed through fixed structural extractors spanning six receptive fields, from blind spot local aggregation to directional log-ratio region contrast, and fused via learnable weights into one unified supervision signal for masked reconstruction. On 12 SAR benchmarks across classification, detection, and segmentation, SARATR-X-v2 achieves state-of-the-art transfer performance. Under synthetic speckle variation, the proposed target reduces perturbation drift in the learned supervision by nearly two orders of magnitude relative to pixel-space supervision. Taken together, these results support physics-grounded stability and semantic scale compatibility as a principled framework for pretraining target design under coherent imaging, and they suggest that effective SAR pretraining is not about reconstructing more signal but about reconstructing the right structural target.