Variational Dual-path Attention Network for CSI-Based Gesture Recognition

TL;DR

This paper introduces VDAN, a lightweight, interpretable neural network that refines CSI features for Wi-Fi gesture recognition, improving robustness and efficiency on resource-limited devices.

Contribution

It proposes a novel variational dual-path attention network that leverages frequency and temporal sparsity, with uncertainty modeling for enhanced robustness.

Findings

Attention weights align with physical CSI sparsity

Improved robustness to noise demonstrated

Efficient processing suitable for edge devices

Abstract

Wi-Fi gesture recognition based on Channel State Information (CSI) is challenged by high-dimensional noise and resource constraints on edge devices. Prevailing end-to-end models tightly couple feature extraction with classification, overlooking the inherent time-frequency sparsity of CSI and leading to redundancy and poor generalization. To address this, this paper proposes a lightweight feature preprocessing module--the Variational Dual-path Attention Network (VDAN). It performs structured feature refinement through frequency-domain filtering and temporal detection. Variational inference is introduced to model the uncertainty in attention weights, thereby enhancing robustness to noise. The design principles of the module are explained from the perspectives of the information bottleneck and regularization. Experiments on a public dataset demonstrate that the learned attention weights align with the physical sparse characteristics of CSI, verifying its interpretability. This work provides an efficient and explainable front-end processing solution for resource-constrained wireless sensing systems.