We present RelCon, a novel self-supervised Relative Contrastive learning approach for training a motion foundation model from wearable accelerometry sensors. First, a learnable distance measure is trained to capture motif similarity and domain-specific semantic information such as rotation invariance. Then, the learned distance provides a measurement of semantic similarity between a pair of accelerometry time-series, which we use to train our foundation model to model relative relationships across time and across subjects. The foundation model is trained on 1 billion segments from 87,376 participants, and achieves state-of-the-art performance across multiple downstream tasks, including human activity recognition and gait metric regression. To our knowledge, we are the first to show the generalizability of a foundation model with motion data from wearables across distinct evaluation tasks.
Cite
@article{arxiv.2411.18822,
title = {RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data},
author = {Maxwell A. Xu and Jaya Narain and Gregory Darnell and Haraldur Hallgrimsson and Hyewon Jeong and Darren Forde and Richard Fineman and Karthik J. Raghuram and James M. Rehg and Shirley Ren},
journal= {arXiv preprint arXiv:2411.18822},
year = {2025}
}
Comments
Accepted to ICLR 2025. Code here: https://github.com/maxxu05/relcon