-
[pdf]
[supp]
[bibtex]@InProceedings{Shenaj_2023_WACV, author = {Shenaj, Donald and Fan{\`\i}, Eros and Toldo, Marco and Caldarola, Debora and Tavera, Antonio and Michieli, Umberto and Ciccone, Marco and Zanuttigh, Pietro and Caputo, Barbara}, title = {Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {444-454} }
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
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. The code is available at https://github.com/Erosinho13/LADD.
Related Material