Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
This addresses domain adaptation in federated learning for semantic segmentation, enabling use with unlabeled client data, but it is incremental as it builds on existing FL and domain adaptation techniques.
The paper tackles the problem of domain shift in semantic segmentation within federated learning where client data is unlabeled, proposing a new task called FFREEDA and a method called LADD that uses self-supervision and style-based clustering, resulting in outperformance over existing approaches.
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.