让雷达目标检测模型在树莓派上高效运行，性能提升同时大幅降低资源消耗。
DSFEC: Efficient and Deployable Deep Radar Object Detection
- 用深度可分离卷积和新型特征增强压缩模块优化网络结构
- 提出DSFEC-L系列模型，在nuScenes上实现14.6%性能提升、78.5%计算量减少
- 部署版模型在树莓派上运行速度提升74.5%，适合边缘设备实时应用
将雷达目标检测模型部署到树莓派等资源受限的边缘设备面临巨大挑战，主要源于模型体积大、计算能力与内存有限。本文探索深度可分离卷积在雷达目标检测网络中的效率，并将其集成到模型中。同时，引入一种新型特征增强与压缩（FEC）模块到PointPillars特征编码器中以进一步提升性能。基于这些创新，提出DSFEC-L模型及其两个版本：1）高效版DSFEC-M在nuScenes数据集上实现14.6%的性能提升，计算量减少60%；2）可部署版DSFEC-S实现3.76%性能提升，计算量减少78.5%。尽管性能增益微小，其部署模型在树莓派上的运行时间相较基线减少74.5%。
原文摘要 · Abstract (English)
Deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi poses significant challenges due to the large size of the model and the limited computational power and the memory of the Pi. In this work, we explore the efficiency of Depthwise Separable Convolutions in radar object detection networks and integrate them into our model. Additionally, we introduce a novel Feature Enhancement and Compression (FEC) module to the PointPillars feature encoder to further improve the model performance. With these innovations, we propose the DSFEC-L model and its two versions, which outperform the baseline (23.9 mAP of Car class, 20.72 GFLOPs) on nuScenes dataset: 1). An efficient DSFEC-M model with a 14.6% performance improvement and a 60% reduction in GFLOPs. 2). A deployable DSFEC-S model with a 3.76% performance improvement and a remarkable 78.5% reduction in GFLOPs. Despite marginal performance gains, our deployable model achieves an impressive 74.5% reduction in runtime on the Raspberry Pi compared to the baseline.
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。