Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2411.18822 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915236499423232 |
|---|---|
| author | Xu, Maxwell A. Narain, Jaya Darnell, Gregory Hallgrimsson, Haraldur Jeong, Hyewon Forde, Darren Fineman, Richard Raghuram, Karthik J. Rehg, James M. Ren, Shirley |
| author_facet | Xu, Maxwell A. Narain, Jaya Darnell, Gregory Hallgrimsson, Haraldur Jeong, Hyewon Forde, Darren Fineman, Richard Raghuram, Karthik J. Rehg, James M. Ren, Shirley |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18822 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data Xu, Maxwell A. Narain, Jaya Darnell, Gregory Hallgrimsson, Haraldur Jeong, Hyewon Forde, Darren Fineman, Richard Raghuram, Karthik J. Rehg, James M. Ren, Shirley Signal Processing Artificial Intelligence Machine Learning 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. |
| title | RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data |
| topic | Signal Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.18822 |