Self-supervised learning (SSL) for WiFi-based human activity recognition
(HAR) holds great promise due to its ability to address the challenge of
insufficient labeled data. However, directly transplanting SSL algorithms,
especially contrastive learning, originally designed for other domains to CSI
data, often fails to achieve the expected performance. We attribute this issue
to the inappropriate alignment criteria, which disrupt the semantic distance
consistency between the feature space and the input space. To address this
challenge, we introduce \textbf{A}netenna \textbf{R}esponse
\textbf{C}onsistency (ARC) as a solution to define proper alignment criteria.
ARC is designed to retain semantic information from the input space while
introducing robustness to real-world noise. We analyze ARC from the perspective
of CSI data structure, demonstrating that its optimal solution leads to a
direct mapping from input CSI data to action vectors in the feature map.
Furthermore, we provide extensive experimental evidence to validate the
effectiveness of ARC in improving the performance of self-supervised learning
for WiFi-based HAR.

通过引入 Anetenna Response Consistency (ARC) 作为解决方案来定义适当的对准准则，本研究分析了 ARC 的 CSI 数据结构视角，并且通过提供大量的实验证据来验证 ARC 在提高基于 WiFi 的自监督学习在人类活动识别中的性能方面的有效性。