Paper accepted at WACV 2023

Our work “Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning”, done in collaboration with VANDAL research group of Politecnico di Torino, has been accepted at WACV 2023, held in Hawaii.

TL;DR: We propose the novel task of Federated source-Free Domain Adaptation (FFREEDA) in which the clients’ data is unlabeled and the server accesses a source labeled dataset for pre-training only. To solve FFREEDA we propose LADD which leverages the knowledge of the pre-trained model by employing self-supervision with ad-hoc regularization techniques for local training and introducing a novel federated clustered aggregation scheme based on the clients’ style.

Many thanks to the co-authors: Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh and Barbara Caputo for their important contribution.

Paper: https://arxiv.org/abs/2210.02326

Code: https://github.com/Erosinho13/LADD