Multi-source Domain Adaptation (MDA) aims to adapt models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we introduce our approach as a collaborative MDA framework, which comprises two adaptation phases. Firstly, we conduct domain adaptation for each source individually with the target, utilizing optimal transport. Then, in the second phase, which constitutes the final part of the framework, we design the architecture of centralized federated learning to collaborate the N models representing the N sources. This architecture offers the advantage of using the sources without accessing their data, thus resolving data privacy issues inherent in domain adaptation. Additionally, during this phase, the server guides and fine-tunes the adaptation using a small number of pseudo-labeled samples available in the target domain, referred to as the target validation subset of the dataset.
View on arXiv