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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Strohmayer, Julian, Sterzinger, Rafael, Wödlinger, Matthias, Kampel, Martin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910706000986112
author Strohmayer, Julian
Sterzinger, Rafael
Wödlinger, Matthias
Kampel, Martin
author_facet Strohmayer, Julian
Sterzinger, Rafael
Wödlinger, Matthias
Kampel, Martin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13284
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition
Strohmayer, Julian
Sterzinger, Rafael
Wödlinger, Matthias
Kampel, Martin
Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
Machine Learning
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.
title DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2411.13284