用蒙特卡洛树搜索找轻量雷达目标检测网络
Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search
- 用蒙特卡洛树搜索自动寻找高效神经网络结构
- 新网络检测率达标且比人工设计模型轻得多
- 适合资源受限的嵌入式雷达系统部署
近期研究证明深度神经网络在复杂环境（如杂波、干扰、多目标）下具备优异的雷达目标检测能力，但其通常较高的计算复杂度限制了在嵌入式雷达系统中的广泛应用。本文提出基于蒙特卡洛树搜索（MCTS）的新型神经架构搜索（NAS）方法，旨在找到在保证检测性能的同时显著降低计算开销的网络结构。我们在端到端杂波雷达信号上评估所搜寻架构的性能指标与泛化能力。结果表明，所提出的新型网络在满足所需检测概率的前提下，显著轻于专家设计的基准模型。
原文摘要 · Abstract (English)
Recent research works establish deep neural networks as high performing tools for radar target detection, especially on challenging environments (presence of clutter or interferences, multi-target scenarii...). However, the usually large computational complexity of these networks is one of the factors preventing them from being widely implemented in embedded radar systems. We propose to investigate novel neural architecture search (NAS) methods, based on Monte-Carlo Tree Search (MCTS), for finding neural networks achieving the required detection performance and striving towards a lower computational complexity. We evaluate the searched architectures on endoclutter radar signals, in order to compare their respective performance metrics and generalization properties. A novel network satisfying the required detection probability while being significantly lighter than the expert-designed baseline is proposed.
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。