发表机构
Aerospace Information Research Institute, Chinese Academy of Sciences; University of Chinese Academy of Sciences（中国科学院空天信息创新研究院; 中国科学院大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对少样本跨传感器SAR目标检测的域适应问题，提出散射感知专家分解框架，通过共享路径与散射特定专家路径实现域对齐与异质响应补偿，在双向异质SAR检测任务中性能优越。
AI 中文摘要
合成孔径雷达（SAR）目标检测是遥感解译的重要组成部分。然而，由于频段、分辨率、背景杂波和目标散射响应的差异，现有检测器在训练和测试数据来自不同SAR域时性能往往会下降。尽管域适应方法为解决该问题提供了有前景的范式，但大多数方法主要追求域不变特征对齐，会抑制对目标检测有用的传感器相关散射特性。在少样本场景下，该问题更具挑战性，此时仅能获取少量带完整标注的目标域SAR图像。为解决该问题，本文提出一种面向少样本SAR域适应目标检测的散射感知共享-特定特征分解框架。我们将检测特征分解为共享路径和多个软门控散射特定专家路径：共享路径学习可迁移的目标结构信息，用于非对称域对齐；散射特定专家则自适应补偿异质SAR响应。此外，引入路由域辅助损失以鼓励特定专家捕获传感器相关路由偏好，还使用专家平衡损失防止路由崩溃。我们在FARAD-X/FARAD-Ka与MiniSAR之间的四个双向异质SAR检测任务上，针对不同少样本设置开展了大量实验，实验结果表明，所提方法在正向和反向适应方向上均实现了优越性能。
英文摘要
Synthetic aperture radar (SAR) object detection is an important part of remote sensing interpretation. However, because of variations in frequency band, resolution, background clutter, and target scattering responses, the performance of existing detectors often degrades when training and testing data are acquired from different SAR domains. Although domain adaptation methods offer a promising paradigm for solving this problem, most of them mainly pursue domain-invariant feature alignment and suppress sensor-dependent scattering characteristics that are useful for object detection. This problem becomes more challenging in few-shot scenarios, where only a few fully annotated target-domain SAR images are available. To address this issue, we propose a scattering-aware shared-specific feature decomposition framework for few-shot SAR domain adaptation object detection. We decompose detection features into a shared path and several soft-gated scattering-specific expert paths. The shared path learns transferable object structural information and is used for asymmetric domain alignment, while the scattering-specific experts adaptively compensate heterogeneous SAR responses. In addition, routing-domain auxiliary loss is introduced to encourage specific experts to capture sensor-dependent routing preferences, and an expert balancing loss is used to prevent routing collapse. Extensive experiments on four bidirectional heterogeneous SAR detection tasks between FARAD-X/FARAD-Ka and MiniSAR under different few-shot settings have been conducted and experimental results demonstrate that the proposed method achieves superior performance in both forward and reverse adaptation directions.
CommentsSubmitted to IEEE JSTARS. 13 pages, 7 figures
