Few-shot learning is a machine learning paradigm in which a model is trained to generalize effectively from only a small number of labeled examples, often by leveraging prior knowledge or meta-learning strategies to adapt quickly to new tasks or domains. In WiFi/CSI-based sensing, it is particularly valuable because collecting large amounts of labeled CSI data in real-world environments is costly and time-consuming, and systems must frequently adapt to new locations, hardware configurations, or user populations where only minimal data is available. Key variants relevant to this field include domain-agnostic approaches that explicitly address cross-domain deployment challenges, as seen in frameworks like DASECount, where few-shot learning enables sample-efficient crowd counting across environments without requiring extensive recalibration or data collection at each new site.
Source Papers
- A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Channels ↗ — A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Cha
- DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-Shot Learning ↗ — DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired