CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision

TL;DR

CSI-JEPA introduces a self-supervised learning framework for Wi-Fi sensing that learns reusable representations from unlabeled CSI data, significantly reducing the need for labeled data and improving multi-task sensing performance.

Contribution

It proposes a novel self-supervised predictive learning method tailored for CSI data, with a channel variation-aware masking strategy and multi-task adaptation, enhancing label efficiency and generalization.

Findings

Achieves up to 10.64% accuracy improvement over supervised models.

Reduces labeled data requirements by up to 98%.

Improves performance across seven diverse Wi-Fi sensing tasks.

Abstract

Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usually rely on task-specific supervised training and require substantial labeled data for each task, device, user, or environment. This limits their scalability in practical deployments where unlabeled CSI is abundant but labeled data is costly to collect. In this paper, we present CSI-JEPA, a self-supervised predictive representation learning framework for label-efficient, multi-task Wi-Fi sensing. CSI-JEPA learns reusable temporal-spectral representations from unlabeled CSI samples by predicting latent features of masked channel regions from visible context. To better match the physical structure of CSI, CSI-JEPA tokenizes channel-response amplitude windows along the time and subcarrier dimensions. It then introduces a channel variation-aware masking strategy that samples predictive targets from regions with stronger local temporal and subcarrier-domain variations. After pretraining, the encoder is frozen and used as a backbone, with lightweight task-specific adapters added for downstream sensing tasks. We evaluate CSI-JEPA on seven real-world Wi-Fi sensing tasks spanning diverse objectives and deployment settings. The results show that CSI-JEPA improves downstream sensing performance over competitive baselines, achieving up to 10.64 percentage points mean accuracy gain over state-of-the-art supervised Transformer and matched-budget label savings of up to 98.0%.