通过关系几何迁移，让轻量模型在雷达船检测中超越大模型性能。
Lightweight SAR Ship Detection via Contrastive Distillation
- 用对比学习在共享空间传递目标间几何关系，而非简单匹配特征
- 在两个数据集上使轻量模型提升6.2 mAP，甚至超过教师模型
- 适用于各类检测架构，无需修改原有网络结构
基于深度卷积和变压器的检测器在合成孔径雷达（SAR）船检测中表现优异，但计算开销大，难以实现实时或机载部署。轻量级模型虽效率高，却难以捕捉SAR后向散射中复杂的结构关系。现有知识蒸馏方法多依赖特征或输出概率匹配，仅强化局部激活相似性，忽略目标表示间的几何关系。本文提出一种面向SAR船检测的结构化统一关系知识蒸馏框架（SURGE），通过对比信息最大化（InfoNCE）目标，在共享投影空间中将强教师模型的关系几何传递给紧凑学生模型。据我们所知，这是首个基于变压器的SAR领域知识蒸馏框架。该框架具有架构无关性，可为两阶段、单阶段及变压器类检测器提供统一的区域级蒸馏接口，无需修改其部署结构。在SSDD和HRSID基准上的实验表明，该方法显著提升了两阶段检测器性能，学生模型相比基线最高提升6.2 mAP与8.0 AP75，甚至超越教师模型表现。
原文摘要 · Abstract (English)
Deep convolutional and transformer-based detectors achieve strong performance for SAR ship detection but are often computationally prohibitive for real-time or onboard deployment. Lightweight models offer improved efficiency yet struggle to capture the complex structural relationships inherent in SAR backscatter. Most existing SAR knowledge-distillation approaches rely on feature or logit matching, which enforces localized activation similarity while neglecting the geometric relationships among object representations. We propose a Structured Unified Relational knowledGE distillation framework for SAR Ship detection (SURGE) that transfers relational geometry from a powerful teacher detector to a compact student detector using a contrastive InfoNCE objective in a shared projection embedding space. To the best of our knowledge, this work presents the first transformer-based SAR ship detector knowledge distillation framework in SAR domain. The framework is architecture-agnostic in the sense that it provides a common region-level distillation interface for two-stage, one-stage and transformer-based detectors without modifying their deployed architectures. Experiments on the SSDD and HRSID benchmarks demonstrate that the proposed method yields substantial improvements for two-stage detectors, achieving up to 6.2 mAP and 8.0 AP75 gains over baseline student and even surpassing teacher performance
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。