Federated Online Adaptation for Deep Stereo
Abstract
We introduce a novel approach for adapting deep stereo networks in a collaborative manner. By building over principles of federated learning we develop a distributed framework allowing for demanding the optimization process to a number of clients deployed in different environments. This makes it possible for a deep stereo network running on resourced-constrained devices to capitalize on the adaptation process carried out by other instances of the same architecture and thus improve its accuracy in challenging environments even when it cannot carry out adaptation on its own. Experimental results show how federated adaptation performs equivalently to on-device adaptation and even better when dealing with challenging environments.
Cite
Text
Poggi and Tosi. "Federated Online Adaptation for Deep Stereo." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.01906Markdown
[Poggi and Tosi. "Federated Online Adaptation for Deep Stereo." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/poggi2024cvpr-federated/) doi:10.1109/CVPR52733.2024.01906BibTeX
@inproceedings{poggi2024cvpr-federated,
title = {{Federated Online Adaptation for Deep Stereo}},
author = {Poggi, Matteo and Tosi, Fabio},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {20165-20175},
doi = {10.1109/CVPR52733.2024.01906},
url = {https://mlanthology.org/cvpr/2024/poggi2024cvpr-federated/}
}