DeepSenseMoE: Harnessing Power of Time Series Foundation Models for Few-Shot Human Activity Recognition

Recent advances in Time Series Foundation Models (TSFMs) have fundamentally revolutionized general time series analysis across domains like finance, retail, weather, and power. However, how to unlock the hidden capacity of generalpurpose TSFMs for wearable activity recognition still remains largely unexplored, given severe sensor annotation scarcity and highly heterogeneous sensor data. To address these challenges, we propose DeepSenseMoE-a novel multi-scale convolution-based Mixture of Experts (MoE) module for parameter-efficient fine-tuning of general-purpose TSFMs to sensor-based activity recognition. DeepSenseMoE integrates three key innovations: (1) Multi-scale convolutional experts with different filter sizes responsible for capturing varying sensor contexts; (2) Shared-expert isolation mechanism compressing common activity knowledge into a single shared expert while reducing redundancy among routed experts; and (3) Hierarchical supervised contrastive alignment guiding experts to further learn discriminative activity features. Extensive experiments on three challenging HAR benchmarks demonstrate DeepSenseMoE's superiority, achieving up to 9.5% accuracy gains over state-of-the-art under few-shot and full-supervised settings, with only <1% additional trainable parameters. We hope that this work may lay a solid foundation to accelerate development and deployment of powerful TSFMs in data-scarce wearable activity recognition tasks while reducing the reliance on labeled sensor data.