XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge
This addresses the challenge of adapting deep learning models for edge-based human sensing applications with minimal data and computational overhead, though it appears incremental in improving transfer methods.
The paper tackles the problem of transferring pre-trained models for human sensing on edge systems with limited sensor data and resources, proposing XTransfer which achieves state-of-the-art performance while reducing data collection, training, and deployment costs.
Deep learning for human sensing on edge systems presents significant potential for smart applications. However, its training and development are hindered by the limited availability of sensor data and resource constraints of edge systems. While transferring pre-trained models to different sensing applications is promising, existing methods often require extensive sensor data and computational resources, resulting in high costs and poor adaptability in practice. In this paper, we propose XTransfer, a first-of-its-kind method enabling modality-agnostic, few-shot model transfer with resource-efficient design. XTransfer flexibly uses single or multiple pre-trained models and transfers knowledge across different modalities by (i) model repairing that safely mitigates modality shift by adapting pre-trained layers with only few sensor data, and (ii) layer recombining that efficiently searches and recombines layers of interest from source models in a layer-wise manner to create compact models. We benchmark various baselines across diverse human sensing datasets spanning different modalities. Comprehensive results demonstrate that XTransfer achieves state-of-the-art performance while significantly reducing the costs of sensor data collection, model training, and edge deployment.