Federated Multi-Target Domain Adaptation
This work addresses privacy-preserving model training for vision tasks in federated settings with unlabeled data, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of training models on distributed unlabeled client data with a centralized labeled source, addressing domain shifts between server and clients, and proposes a DualAdapt method that achieves high accuracy with minimal communication and computational costs.
Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision tasks. Unlike typical federated settings with labeled client data, we consider a more practical scenario where the distributed client data is unlabeled, and a centralized labeled dataset is available on the server. We further take the server-client and inter-client domain shifts into account and pose a domain adaptation problem with one source (centralized server data) and multiple targets (distributed client data). Within this new Federated Multi-Target Domain Adaptation (FMTDA) task, we analyze the model performance of exiting domain adaptation methods and propose an effective DualAdapt method to address the new challenges. Extensive experimental results on image classification and semantic segmentation tasks demonstrate that our method achieves high accuracy, incurs minimal communication cost, and requires low computational resources on client devices.