Statistically-Guided Meta-Learning for Cross-Deployment Activity Recognition in Distributed Fiber-Optic Sensing

TL;DR

This paper introduces DUPLE, a meta-learning framework for fiber-optic sensing that improves activity recognition across deployments by leveraging dual-domain cues and adaptive class representations.

Contribution

DUPLE is a novel prototype-based meta-learning approach that jointly exploits time- and frequency-domain information for cross-deployment recognition in DFOS.

Findings

DUPLE outperforms existing deep learning and meta-learning methods on real-world benchmarks.

It achieves more accurate recognition with fewer labels in new deployment sites.

The framework demonstrates stable performance across diverse deployment conditions.

Abstract

Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: severe cross-deployment domain shift, scarce or unavailable labels at new sites, and limited within-class coverage even in source deployments. We propose DUPLE, a prototype-based meta-learning framework tailored for cross-deployment DFOS recognition. The core idea is to jointly exploit complementary time- and frequency-domain cues and adapt class representations to sample-specific statistics: (i) a dual-domain learner constructs multi-prototype class representations to cover intra-class heterogeneity; (ii) a lightweight statistical guidance mechanism estimates the reliability of each domain from raw signal statistics; and (iii) a query-adaptive aggregation strategy selects and combines the most relevant prototypes for each query. Extensive experiments on two real-world cross-deployment benchmarks demonstrate consistent improvements over strong deep learning and meta-learning baselines, achieving more accurate and stable recognition under label-scarce target deployments.