WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
Yin Li, Rajalakshmi Nandakumar
TL;DR
The paper tackles data scarcity and poor generalization in wireless perception by introducing WixUp, a general, training-free mixing-based data augmentation framework that converts heterogeneous wireless data into lossless range-profile representations via Gaussian mixtures and intersection-based synthesis. WixUp enables robust data diversification across datasets, model architectures, tasks, and sensing modalities, and extends to unsupervised domain adaptation through self-training, reducing labeling needs in new environments or users. It provides a unified pipeline with components for inverse coordinate mapping, intersection-based mixing, bootstrapping, and angle enrichment, and demonstrates consistent improvements over baselines across mmWave and acoustic datasets, multiple tasks, and architectures. The work offers practical impact by enhancing model robustness under occlusion and noise, enabling cross-domain applicability, and delivering an open framework for broader wireless sensing research and deployment.
Abstract
Recent advancements in wireless perception technologies, including mmWave, WiFi, and acoustics, have expanded their application in human motion tracking and health monitoring. They are promising alternatives to traditional camera-based perception systems, thanks to their efficacy under diverse conditions or occlusions, and enhanced privacy. However, the integration of deep learning within this field introduces new challenges such as the need for extensive training data and poor model generalization, especially with sparse and noisy wireless point clouds. As a remedy, data augmentation is one solution well-explored in other deep learning fields, but they are not directly applicable to the unique characteristics of wireless signals. This motivates us to propose a custom data augmentation framework, WixUp, tailored for wireless perception. Moreover, we aim to make it a general framework supporting various datasets, model architectures, sensing modalities, and tasks; while previous wireless data augmentation or generative simulations do not exhibit this generalizability, only limited to certain use cases. More specifically, WixUp can reverse-transform lossy coordinates into dense range profiles using Gaussian mixture and probability tricks, making it capable of in-depth data diversity enhancement; and its mixing-based method enables unsupervised domain adaptation via self-training, allowing training of the model with no labels from new users or environments in practice. In summary, our extensive evaluation experiments show that WixUp provides consistent performance improvement across various scenarios and outperforms the baselines.