Computer Vision Self-supervised Learning Methods on Time Series
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911765524119552 |
|---|---|
| author | Lee, Daesoo Aune, Erlend |
| author_facet | Lee, Daesoo Aune, Erlend |
| contents | Self-supervised learning (SSL) has had great success in both computer vision. Most of the current mainstream computer vision SSL frameworks are based on Siamese network architecture. These approaches often rely on cleverly crafted loss functions and training setups to avoid feature collapse. In this study, we evaluate if those computer-vision SSL frameworks are also effective on a different modality (\textit{i.e.,} time series). The effectiveness is experimented and evaluated on the UCR and UEA archives, and we show that the computer vision SSL frameworks can be effective even for time series. In addition, we propose a new method that improves on the recently proposed VICReg method. Our method improves on a \textit{covariance} term proposed in VICReg, and in addition we augment the head of the architecture by an iterative normalization layer that accelerates the convergence of the model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2109_00783 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Computer Vision Self-supervised Learning Methods on Time Series Lee, Daesoo Aune, Erlend Machine Learning Artificial Intelligence Self-supervised learning (SSL) has had great success in both computer vision. Most of the current mainstream computer vision SSL frameworks are based on Siamese network architecture. These approaches often rely on cleverly crafted loss functions and training setups to avoid feature collapse. In this study, we evaluate if those computer-vision SSL frameworks are also effective on a different modality (\textit{i.e.,} time series). The effectiveness is experimented and evaluated on the UCR and UEA archives, and we show that the computer vision SSL frameworks can be effective even for time series. In addition, we propose a new method that improves on the recently proposed VICReg method. Our method improves on a \textit{covariance} term proposed in VICReg, and in addition we augment the head of the architecture by an iterative normalization layer that accelerates the convergence of the model. |
| title | Computer Vision Self-supervised Learning Methods on Time Series |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2109.00783 |