RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data

TL;DR

RelCon introduces a self-supervised contrastive learning method for wearable motion data, training a foundation model that captures semantic similarities and generalizes well across various activity recognition tasks.

Contribution

It proposes a novel relative contrastive learning approach with a learnable distance measure for wearable accelerometry data, enabling a generalizable motion foundation model.

Findings

Achieved state-of-the-art results on multiple downstream tasks.

Trained on 1 billion segments from over 87,000 participants.

First to demonstrate generalizability of a motion foundation model across tasks.

Abstract

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.