UniCSI Towards a Universal Wi-Fi CSI Encoder for Ubiquitous Human Sensing
To bridge this gap, we present UniCSI, a unified foundation architecture that directly operates on heterogeneous CSI while preserving the integrity of the native waveform.
ProofPaper ↗
Key points
- Wi-Fi sensing promises to turn the everyday wireless signals that already surround us into ubiquitous sensors for human sensing.
- UniCSI hinges on two core innovations: (1) a physics-informed RF tokenizer that encodes each frequency channel based on its fractional position within the physical spectrum rather than rigid array indices.
- (2) a spectral aggregator that distills variable-length channel sequences into a fixed-size spectral signature, effectively decoupling the feature dimensionality from the physical subcarrier spacing.
- Extensive evaluations on a large-scale corpus of 25 heterogeneous public datasets, spanning 14 to 2048 subcarriers, 20 to 160 MHz bandwidth, and the 2.4 and 5 GHz bands, demonstrate that native heterogeneous ingestion substantially improves cross-domain transfer under both supervised and self-supervised training schemes, particularly in regimes where fixed-grid architectures fail to generalize.
Sources (1)
- [1]UniCSI Towards a Universal Wi-Fi CSI Encoder for Ubiquitous Human SensingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 07:00 AM
To bridge this gap, we present UniCSI, a unified foundation architecture that directly operates on heterogeneous CSI while preserving the integrity of the native waveform.
Wi-Fi sensing promises to turn the everyday wireless signals that already surround us into ubiquitous sensors for human sensing.
Extractive summary: sentences quoted from the sources.