Scenario-Agnostic Deep-Learning-Based Localization with Contrastive Self-Supervised Pre-training

TL;DR

This paper introduces CSSLoc, a contrastive self-supervised learning framework that enhances wireless localization accuracy across various scenarios by learning environment-agnostic representations without requiring labeled location data.

Contribution

CSSLoc is the first to apply contrastive self-supervised pre-training for scenario-agnostic wireless localization, improving generality and robustness without supervision.

Findings

Outperforms classical localization methods in indoor scenarios

Achieves higher robustness to environmental dynamics

Enables transfer learning for downstream localization tasks

Abstract

Wireless localization has become a promising technology for offering intelligent location-based services. Although its localization accuracy is improved under specific scenarios, the short of environmental dynamic vulnerability still hinders this approach from being fully practical applications. In this paper, we propose CSSLoc, a novel framework on contrastive self-supervised pre-training to learn generic representations for accurate localization in various scenarios. Without the location information supervision, CSSLoc attempts to learn an insightful metric on the similarity discrimination of radio data, in such a scenario-agnostic manner that the similar samples are closely clustered together and different samples are separated in the representation space. Furthermore, the trained feature encoder can be directly transferred for downstream localization tasks, and the location predictor is trained to estimate accurate locations with the robustness of environmental dynamics. With extensive experimental results, CSSLoc can outperform classical and state-of-the-art DNN-based localization schemes in typical indoor scenarios, pushing deep-learning-based localization from specificity to generality.