DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition

TL;DR

This paper introduces DATTA, a novel framework for improving WiFi-based human activity recognition across different environments by combining domain-adversarial training, test-time adaptation, and weight resetting, ensuring real-time performance and robustness.

Contribution

The paper presents DATTA, a new domain-adversarial test-time adaptation method specifically designed for cross-domain WiFi-based sensing, enhancing generalization and preventing catastrophic forgetting.

Findings

DATTA improves F1-Score by 8.1% over state-of-the-art methods.

The framework is lightweight and suitable for real-time applications.

Comprehensive ablation studies validate the effectiveness of key components.

Abstract

Cross-domain generalization is an open problem in WiFi-based sensing due to variations in environments, devices, and subjects, causing domain shifts in channel state information. To address this, we propose Domain-Adversarial Test-Time Adaptation (DATTA), a novel framework combining domain-adversarial training (DAT), test-time adaptation (TTA), and weight resetting to facilitate adaptation to unseen target domains and to prevent catastrophic forgetting. DATTA is integrated into a lightweight, flexible architecture optimized for speed. We conduct a comprehensive evaluation of DATTA, including an ablation study on all key components using publicly available data, and verify its suitability for real-time applications such as human activity recognition. When combining a SotA video-based variant of TTA with WiFi-based DAT and comparing it to DATTA, our method achieves an 8.1% higher F1-Score. The PyTorch implementation of DATTA is publicly available at: https://github.com/StrohmayerJ/DATTA.