Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.22726 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913164823625728 |
|---|---|
| author | Zhang, Yu Zhang, Xi Zhou, Hualin Chen, Xinyuan Gao, Shang Jia, Hong Yang, Jianfei Qi, Yuankai Gu, Tao |
| author_facet | Zhang, Yu Zhang, Xi Zhou, Hualin Chen, Xinyuan Gao, Shang Jia, Hong Yang, Jianfei Qi, Yuankai Gu, Tao |
| contents | 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 limited transferability. 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 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 restructure models. We benchmark various baselines across diverse human sensing datasets spanning different modalities. The results show that XTransfer achieves state-of-the-art performance while significantly reducing the costs of sensor data collection, model training, and edge deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge Zhang, Yu Zhang, Xi Zhou, Hualin Chen, Xinyuan Gao, Shang Jia, Hong Yang, Jianfei Qi, Yuankai Gu, Tao Computer Vision and Pattern Recognition Machine Learning 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 limited transferability. 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 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 restructure models. We benchmark various baselines across diverse human sensing datasets spanning different modalities. The results show that XTransfer achieves state-of-the-art performance while significantly reducing the costs of sensor data collection, model training, and edge deployment. |
| title | XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.22726 |