MHD-Protonet: Margin-Aware Hard Example Mining for SAR Few-Shot Learning via Dual-Loss Optimization

Abstract

Synthetic aperture radar (SAR) image classification under limited data conditions faces two major challenges: inter-class similarity, where distinct radar targets (e.g., tanks and armored trucks) have nearly identical scattering characteristics, and intra-class variability, caused by speckle noise, pose changes, and differences in depression angle. To address these challenges, we propose MHD-ProtoNet, a meta-learning framework that extends prototypical networks with two key innovations: margin-aware hard example mining to better separate confusable classes by enforcing prototype distance margins, and dual-loss optimization to refine embeddings and improve robustness to noise-induced variations. Evaluated on the MSTAR dataset in a five-way one-shot task, MHD-ProtoNet achieves (Formula presented.) accuracy, outperforming the Hybrid Inference Network (HIN) (Formula presented.), as well as standard few-shot methods such as prototypical networks (Formula presented.), ST-PN (Formula presented.), and graph-based models like ADMM-GCN (Formula presented.) and DGP-NET (Formula presented.). By explicitly mitigating inter-class ambiguity and intra-class noise, the proposed model enables robust SAR target recognition with minimal labeled data.