CIG-MAE: Cross-Modal Information-Guided Masked Autoencoder for Self-Supervised WiFi Sensing

TL;DR

CIG-MAE introduces a self-supervised learning framework for WiFi CSI-based human action recognition, effectively reconstructing amplitude and phase information with adaptive masking and cross-modal alignment, outperforming existing methods.

Contribution

The paper proposes CIG-MAE, a novel cross-modal masked autoencoder with adaptive information-guided masking and a regularizer, tailored for WiFi CSI self-supervised learning.

Findings

Outperforms state-of-the-art SSL methods on public datasets.

Surpasses fully supervised baseline in accuracy.

Demonstrates high data efficiency and robustness.

Abstract

Human Action Recognition using WiFi Channel State Information (CSI) has emerged as an attractive alternative to vision-based methods due to its ubiquity, device-agnostic nature, and inherent privacy-preserving capabilities. However, the high cost of manual annotation and the limited scale of publicly available CSI datasets restrict the performance of supervised approaches. Self-supervised learning (SSL) offers a promising avenue, but existing contrastive paradigms rely on data augmentations that conflict with the physical semantics of radio signals and require large-batch training, making them poorly suited for CSI. To overcome these challenges, we introduce CIG-MAE -- a Cross-modal Information-Guided Masked Autoencoder -- that reconstructs both the amplitude and phase of CSI using a symmetric dual-stream architecture with a high masking ratio. Specifically, we propose an Adaptive Information-Guided Masking strategy that dynamically allocates attention to time-frequency regions with high information density to improve learning efficiency, and incorporate a Barlow Twins regularizer to align cross-modal representations without negative samples. Experiments on three public datasets show that CIG-MAE consistently outperforms SOTA SSL methods and even surpasses a fully supervised baseline, demonstrating superior data efficiency, robustness, and representation generalization.