Adversarial Reweighting with $\alpha$-Power Maximization for Domain Adaptation

arXiv:2404.17275v1 Announce Type: cross
Abstract: The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a novel approach, dubbed Adversarial Reweighting with $\alpha$-Power Maximization (ARPM), for PDA where the source domain contains private classes absent in target domain. In ARPM, we propose a novel adversarial reweighting model that adversarially learns to reweight source domain data to identify source-private class …

abstract adversarial alpha arxiv attention community cs.cv cs.lg domain domain adaptation machine machine learning novel paper power practical set tasks test type universal