Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptation

arXiv:2211.11424v2 Announce Type: replace
Abstract: Unsupervised domain adaptation (UDA) aims to estimate a transferable model for unlabeled target domains by exploiting labeled source data. Optimal Transport (OT) based methods have recently been proven to be a promising solution for UDA with a solid theoretical foundation and competitive performance. However, most of these methods solely focus on domain-level OT alignment by leveraging the geometry of domains for domain-invariant features based on the global embeddings of images. However, global representations of images …

abstract arxiv cs.cv data domain domain adaptation domains foundation hierarchical however modeling performance solid solution source data transport type unsupervised