arXiv cs.AI· Zhoutong Ye, Chengwen Zhang, Zixuan Wang, Xufeng Jian, Zhe He, Qingyang Wan, Xutong Wang, Jiaqi Liu, Mingze Sun, Yu Mei, Chun Yu, Yuanchun Shi·· 4 小时前AI 评分40
IMUDINO：面向惯性感知的自蒸馏基础模型
IMUDINO: Self-distilled Foundation Model for Inertial Sensing
AI 导读
研究者提出 IMUDINO，这是首个在人体活动识别（HAR）、健康监测、动作捕捉与里程计等多种惯性感知任务上均具竞争力的基础模型。该模型将 DINO 自监督学习范式通过保留语义的运动变换适配到惯性数据，并采用带频率感知位置编码的 plain transformer encoder，原生支持可变输入长度与采样率。作者希望其成为通用惯性基础模型的骨干。
正文 · 原文
Authors:Zhoutong Ye, Chengwen Zhang, Zixuan Wang, Xufeng Jian, Zhe He, Qingyang Wan, Xutong Wang, Jiaqi Liu, Mingze Sun, Yu Mei, Chun Yu, Yuanchun Shi
Abstract:We present IMUDINO, the first foundation model (FM) for inertial sensing to achieve competitive performance across diverse sensing tasks including human activity recognition (HAR), health, motion capture, and odometry. Prior inertial FMs often focus on one subfield of inertial sensing and sometimes underperform state-of-the-art supervised methods (e.g., in HAR), making their scope considerably narrower than FMs for vision and natural language. Moreover, they often require fixed input length and sampling rate, and generalize poorly to unseen sensor locations. To build a general-purpose foundation model for inertial sensing, we adapt the DINO self-supervised learning (SSL) paradigm to inertial data through a set of semantics-preserving motion transformations that simulate variations in motion pattern and sensor setup. For model architecture, we use a plain transformer encoder with frequency-aware positional encoding that natively supports varying input length and sampling rate. This simple setup proved remarkably effective for learning global and dense features generalizable across users, sensor setups, tasks, and, in the case of robot odometry, embodiments. We hope IMUDINO can serve as a backbone for inertial sensing and kickstart the development of general-purpose inertial FMs.
| Comments: | Official repo: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2611.07437 [cs.LG] |
| (or arXiv:2611.07437v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07437 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhoutong Ye [view email]
[v1]
Thu, 5 Nov 2026 04:35:16 UTC (12,177 KB)
来源：arXiv cs.AI · arxiv.org