用神经架构搜索优化轻量级SAR目标检测模型
SAR-NAS: Lightweight SAR Object Detection with Neural Architecture Search
- 基于进化搜索优化YOLOv10骨干网络结构
- 在SARDet-100K上实现更高精度与更低计算开销
- 首次将NAS引入SAR目标检测，适合遥感应用
合成孔径雷达（SAR）目标检测面临斑点噪声、小目标模糊和机载计算资源受限等挑战。现有方法多聚焦于SAR专用网络结构设计，本文探索将轻量级检测器YOLOv10应用于SAR检测，并通过神经架构搜索（NAS）提升性能。具体而言，构建了广泛的搜索空间，采用进化搜索系统优化网络结构，尤其关注骨干网络的搜索。所获架构在精度、参数效率与计算成本间取得良好平衡。本工作首次将NAS引入SAR目标检测。在大规模SARDet-100K数据集上的实验表明，优化模型在保持较低计算开销的同时，检测精度优于现有方法。
原文摘要 · Abstract (English)
Synthetic Aperture Radar (SAR) object detection faces significant challenges from speckle noise, small target ambiguities, and on-board computational constraints. While existing approaches predominantly focus on SAR-specific architectural modifications, this paper explores the application of the existing lightweight object detector, i.e., YOLOv10, for SAR object detection and enhances its performance through Neural Architecture Search (NAS). Specifically, we employ NAS to systematically optimize the network structure, especially focusing on the backbone architecture search. By constructing an extensive search space and leveraging evolutionary search, our method identifies a favorable architecture that balances accuracy, parameter efficiency, and computational cost. Notably, this work introduces NAS to SAR object detection for the first time. The experimental results on the large-scale SARDet-100K dataset demonstrate that our optimized model outperforms existing SAR detection methods, achieving superior detection accuracy while maintaining lower computational overhead. We hope this work offers a novel perspective on leveraging NAS for real-world applications.
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。