Abstract
Publications home
Continual adaptation of visual representations via domain randomization and meta-learning
at
| Riccardo Volpi, Diane Larlus, Gregory Rogez |
| Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 4443-4453. |
| arXiv |
| Download |
| Supplementary material |
@InProceedings{Volpi_2021_CVPR,
author = {Volpi, Riccardo and Larlus, Diane and Rogez, Gregory},
title = {Continual Adaptation of Visual Representations via Domain Randomization and Meta-Learning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {4443-4453}
}Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature—the well-known catastrophic forgetting issue. In particular, when a model consecutively learns from different visual domains, it tends to forget the past ones in favor of the most recent. In this context, we show that one way to learn models that are inherently more robust against forgetting is domain randomization—for vision tasks, randomizing the current domain’s distribution with heavy image manipulations. Building on this result, we devise a meta-learning strategy where a regularizer explicitly penalizes any loss associated with transferring the model from the current domain to different “auxiliary” meta-domains, while also easing adaptation to them. Such meta-domains, are also generated through randomized image manipulations. We empirically demonstrate in a variety of experiments—spanning from classification to semantic segmentation—that our approach results in models that are less prone to catastrophic forgetting when transferred to new domains.
Related Content
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.