用轻量Transformer实现高效无线人体感知，实时推理仅需10毫秒。
WiFlexFormer: Efficient WiFi-Based Person-Centric Sensing
- 基于注意力机制设计轻量模型，专为无线信道数据优化
- 推理速度达10毫秒/次，参数量显著低于现有模型
- 适合部署于边缘设备，跨场景泛化能力强
我们提出WiFlexFormer，一种基于Transformer的高效架构，用于基于无线信道状态信息（CSI）的人体中心感知。在与先进视觉模型及专用射频数据处理架构的对比中，WiFlexFormer实现了相当的人体活动识别（HAR）性能，同时参数量更少、推理速度更快。在Nvidia Jetson Orin Nano上，其单次推理时间仅为10毫秒，具备实时推理能力。此外，低参数量有助于提升跨领域泛化性能，常优于更大模型。全面评估表明，WiFlexFormer是高效、可扩展的WiFi感知应用的有力候选方案。PyTorch代码已公开：https://github.com/StrohmayerJ/WiFlexFormer。
原文摘要 · Abstract (English)
We propose WiFlexFormer, a highly efficient Transformer-based architecture designed for WiFi Channel State Information (CSI)-based person-centric sensing. We benchmark WiFlexFormer against state-of-the-art vision and specialized architectures for processing radio frequency data and demonstrate that it achieves comparable Human Activity Recognition (HAR) performance while offering a significantly lower parameter count and faster inference times. With an inference time of just 10 ms on an Nvidia Jetson Orin Nano, WiFlexFormer is optimized for real-time inference. Additionally, its low parameter count contributes to improved cross-domain generalization, where it often outperforms larger models. Our comprehensive evaluation shows that WiFlexFormer is a potential solution for efficient, scalable WiFi-based sensing applications. The PyTorch implementation of WiFlexFormer is publicly available at: https://github.com/StrohmayerJ/WiFlexFormer.
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。