|
|
|
|
Federated adaptation in challenging environments. When facing a domain very different from those observed at training -- e.g., nighttime images (a) -- stereo models suffer drops in accuracy (b). By enabling online adaptation (c) the network can improve its predictions, at the expense of decimating the framerate. In our federated framework, the model can demand the adaptation process to the cloud, to enjoy its benefits while maintaining the original processing speed (d). |
"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." |
| |
1 - Online Adaptation for Stereo
2 - Federated AdaptationWe define a set of active nodes \(A\), capable of adapting independently, and other listening clients \(C\) which demand the adaptation process to the former. The two categories are managed by a central server, in charge of receiving updated weights and distributing them to the listening nodes.
|
| |
| |
| |
@inproceedings{Poggi_2024_CVPR,
author = {Poggi, Matteo and Tosi, Fabio},
title = {Federated Online Adaptation for Deep Stereo},
booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2024},
}