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.

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning / Shenaj, Donald; Fani, Eros; Toldo, Marco; Caldarola, Debora; Tavera, Antonio; Michieli, Umberto; Ciccone, Marco; Zanuttigh, Pietro; Caputo, Barbara. - (In corso di stampa). ((Intervento presentato al convegno IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) tenutosi a Waikoloa, Hawaii (USA) nel 3-7 Gennaio 2023.

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

Fani,Eros;Caldarola,Debora;Tavera,Antonio;Ciccone,Marco;Caputo,Barbara
In corso di stampa

Abstract

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.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2971091