Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

Autor:	Shenaj, Donald, Fanì, Eros, Toldo, Marco, Caldarola, Debora, Tavera, Antonio, Michieli, Umberto, Ciccone, Marco, Zanuttigh, Pietro, Caputo, Barbara
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data. However, most of the existing works on FL unrealistically assume labeled data in the remote clients. Here we propose a novel task (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. Our experiments show that our algorithm is able to efficiently tackle the new task outperforming existing approaches. The code is available at https://github.com/Erosinho13/LADD. Comment: WACV 2023; 11 pages manuscript, 6 pages supplemental material
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2210.02326 Zobrazit plný text záznamu View this record from Arxiv