南京航空航天大学学报（英文版）2025，Vol.42Issue(4)：509-524,16.DOI:10.16356/j.1005-1120.2025.04.007
基于扩散模型和特征迁移的跨载荷SAR数据生成
Cross-Sensor SAR Data Generation Using Diffusion Models and Feature Migration
摘要
Abstract
Different synthetic aperture radar(SAR)sensors vary significantly in resolution,polarization modes,and frequency bands,making it difficult to directly apply existing models to newly launched SAR satellites.These new systems require large amounts of labeled data for model retraining,but collecting sufficient data in a short time is often infeasible.To address this contradiction,this paper proposes a data generation and transfer framework,integrating a stable diffusion model with attention distillation,that leverages historical SAR data to synthesize training data tailored to the unique characteristics of new SAR systems.Specifically,we fine-tune the low-rank adaptation(LoRA)modules within the multimodal diffusion transformer(MM-DiT)architecture to enable class-controllable SAR image generation guided by textual prompts.To ensure that the generated images reflect the statistical properties and imaging characteristics of the target SAR system,we further introduce an attention distillation mechanism that transfers sensor-specific features,such as spatial texture,speckle distribution,and structural patterns,from real target-domain data to the generative model.Extensive experiments on multi-class aircraft target datasets from two real spaceborne SAR systems demonstrate the effectiveness of the proposed approach in alleviating data scarcity and supporting cross-sensor remote sensing applications.关键词
合成孔径雷达/生成技术/跨载荷/特征迁移Key words
synthetic aperture radar(SAR)/generative technology/cross-sensor/feature migration分类
信息技术与安全科学引用本文复制引用
吴宣廷,张帆,马飞,尹嫱,周勇胜..基于扩散模型和特征迁移的跨载荷SAR数据生成[J].南京航空航天大学学报（英文版）,2025,42(4):509-524,16.基金项目
This work was supported in part by the National Natural Science Foundations of China(Nos.62201027,62271034). （Nos.62201027,62271034）
