Description
Source Hypothesis Transfer, or SHOT, is a representation learning framework for unsupervised domain adaptation. SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis.
Papers Using This Method
Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer2021-07-07Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer2020-12-14Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation2020-02-20