WiFlexFormer: Efficient WiFi-Based Person-Centric Sensing

TL;DR

WiFlexFormer is a Transformer-based model for WiFi CSI sensing that achieves real-time performance with fewer parameters, maintaining high accuracy and better cross-domain generalization compared to larger models.

Contribution

This paper introduces WiFlexFormer, a novel efficient Transformer architecture tailored for WiFi-based person-centric sensing, with improved speed and generalization capabilities.

Findings

Achieves comparable HAR accuracy to state-of-the-art models.

Inference time of 10 ms on Nvidia Jetson Orin Nano.

Lower parameter count enhances cross-domain generalization.

Abstract

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.