Federated Online Adaptation for Deep Stereo

2024/05/23 by Matteo Poggi, Fabio Tosi, Poggi, Matteo +1 · 4 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques

paper · pdf · doi:10.48550/arxiv.2405.14873

openalex publication_date 2024/05/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
• Leveraging Sparse LiDAR for RAFT-Stereo: A Depth Pre-Fill Perspective
• NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
• FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity

Related

• Client Adaptation improves Federated Learning with Simulated Non-IID Clients
• FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability
• Efficient Fully Distributed Federated Learning with Adaptive Local Links
• Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency
• Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation