Few-Shot SAR Ship Recognition via Vision Mamba and Scattering Topology Fusion

Source abstract

Synthetic aperture radar (SAR) ship recognition faces great challenges in few-shot scenarios, including insufficient global context modeling, underutilization of physical scattering topological characteristics, and poor generalization capability under limited labeled samples. To address these bottlenecks, this paper proposes a novel few-shot SAR ship recognition method integrating Vision Mamba and scattering topology fusion. A dual-branch complementary architecture is innovatively constructed to learn discriminative features from two heterogeneous perspectives. The visual semantic branch combines residual convolution and state space model in a parallel manner, which empowers simultaneous capture of local fine-grained scattering traits and long-range global structural dependencies, breaking the inherent local receptive-field constraint of conventional CNN-based schemes. The scattering topological branch innovatively introduces graph modeling on extracted strong scattering points, and leverages graph convolutional networks to excavate implicit physical structural priors inherent in SAR ship targets, which are neglected by existing visual-only learning methods. A cross-branch feature fusion strategy is further developed to adaptively aggregate semantic and topological representations, yielding robust feature embedding with strong intra-class compactness and inter-class separability under data scarcity. Experiments on the FUSARShip dataset validate that our method achieves superior performance compared with state-of-the-art competitors in both 1-shot and 5-shot tasks.