DAILOC: Domain-Incremental Learning for Indoor Localization using Smartphones

TL;DR

DAILOC is a domain-incremental learning framework for indoor localization that effectively handles device and temporal domain shifts, significantly improving accuracy over existing methods.

Contribution

It introduces a novel disentanglement strategy and memory-guided class latent alignment to jointly address domain shifts and catastrophic forgetting.

Findings

Achieves up to 2.74x lower average error

Achieves up to 4.6x lower worst-case error

Outperforms state-of-the-art methods across multiple settings

Abstract

Wi-Fi fingerprinting-based indoor localization faces significant challenges in real-world deployments due to domain shifts arising from device heterogeneity and temporal variations within indoor environments. Existing approaches often address these issues independently, resulting in poor generalization and susceptibility to catastrophic forgetting over time. In this work, we propose DAILOC, a novel domain-incremental learning framework that jointly addresses both temporal and device-induced domain shifts. DAILOC introduces a novel disentanglement strategy that separates domain shifts from location-relevant features using a multi-level variational autoencoder. Additionally, we introduce a novel memory-guided class latent alignment mechanism to address the effects of catastrophic forgetting over time. Experiments across multiple smartphones, buildings, and time instances demonstrate that DAILOC significantly outperforms state-of-the-art methods, achieving up to 2.74x lower average error and 4.6x lower worst-case error.