A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning
This work addresses the problem of building interpretable and generalizable foundation models for SAR remote sensing, which is crucial for Earth observation applications, but it appears incremental as it builds on existing vision foundation model concepts with a domain-specific adaptation.
The paper tackled the challenge of insufficient information utilization and poor interpretability in Synthetic Aperture Radar (SAR) image interpretation by proposing a complex-valued SAR foundation model that simulates polarimetric decomposition for pre-training, achieving state-of-the-art results on six downstream tasks with strong generalization in data-scarce conditions.
Vision foundation models in remote sensing have been extensively studied due to their superior generalization on various downstream tasks. Synthetic Aperture Radar (SAR) offers all-day, all-weather imaging capabilities, providing significant advantages for Earth observation. However, establishing a foundation model for SAR image interpretation inevitably encounters the challenges of insufficient information utilization and poor interpretability. In this paper, we propose a remote sensing foundation model based on complex-valued SAR data, which simulates the polarimetric decomposition process for pre-training, i.e., characterizing pixel scattering intensity as a weighted combination of scattering bases and scattering coefficients, thereby endowing the foundation model with physical interpretability. Specifically, we construct a series of scattering queries, each representing an independent and meaningful scattering basis, which interact with SAR features in the scattering query decoder and output the corresponding scattering coefficient. To guide the pre-training process, polarimetric decomposition loss and power self-supervision loss are constructed. The former aligns the predicted coefficients with Yamaguchi coefficients, while the latter reconstructs power from the predicted coefficients and compares it to the input image's power. The performance of our foundation model is validated on six typical downstream tasks, achieving state-of-the-art results. Notably, the foundation model can extract stable feature representations and exhibits strong generalization, even in data-scarce conditions.