Learning Displacement-Aware WiFi Representations for Weakly Supervised Relative Localization
For indoor localization researchers, this work introduces a weakly supervised approach to relative localization, reducing annotation costs compared to absolute positioning methods.
This paper tackles relative localization from WiFi fingerprints without absolute position labels, using weak supervision from inertial sensors. The proposed Intersection Pathway framework learns displacement-aware representations that achieve accurate relative localization across varying displacement ranges.
WiFi fingerprint-based indoor localization has been widely studied, but most existing approaches focus on absolute positioning and rely on dense coordinate annotations, which are costly to obtain at scale. In this paper, we study a fundamentally different problem: relative localization, where the goal is to directly estimate the displacement between two WiFi fingerprint traces without predicting their absolute positions. To reduce annotation overhead, we adopt weak supervision in the form of stepwise motion vectors obtained from inertial sensing. We propose Intersection Pathway (IP), a cross-modal learning framework that aligns fingerprint traces (f-traces) and displacement traces (d-traces) in a shared latent space. The key idea is to enforce an additive structure in the latent space, such that latent addition and subtraction correspond to physical motion composition, enabling direct relative-displacement inference. Experiments on a synthesized dataset derived from real measurements demonstrate that the proposed method learns displacement-aware WiFi representations and achieves accurate relative localization across varying displacement ranges. Furthermore, the learned model can be extended to few-shot absolute localization with sparse anchors.