More is Better: Deep Domain Adaptation with Multiple Sources

arXiv:2405.00749v1 Announce Type: cross
Abstract: In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative. However, direct transfer often results in significant performance decay due to domain shift. Domain adaptation (DA) aims to address this problem by aligning the distributions between the source and target domains. …

abstract alternative applications art arxiv cs.cv cs.lg data domain domain adaptation however knowledge multiple networks neural networks practical scale state train type