Federated Online Adaptation for Deep Stereo

TL;DR

This paper presents a federated learning approach for deep stereo networks that enables collaborative adaptation across devices, improving accuracy in challenging environments without requiring on-device adaptation.

Contribution

It introduces a distributed federated adaptation framework for deep stereo networks, allowing collaborative learning across devices in different environments.

Findings

Federated adaptation matches on-device adaptation performance.

Federated approach outperforms on-device adaptation in challenging environments.

Enables resource-constrained devices to improve stereo accuracy collaboratively.

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.