Bumper-guided representation interpolation for black-box unsupervised domain adaptation

Abstract

Black-box unsupervised domain adaptation (BUDA) presents a challenging scenario in which only unlabeled target data are available, and access to the source model's parameters is limited. Recent BUDA methods that rely on consistency training struggle with error accumulation caused by fixed source representations. In this paper, we propose a novel framework called bumper-guided representation interpolation (BGRI), which introduces a bumper model that interpolates between the source and target domain representation spaces. Using interpolated representations, the bumper model delivers generalized source information and enables stable and effective knowledge transfer to the target model. Through extensive experiments conducted in real-world scenarios across diverse acoustic and linguistic domains, BGRI consistently outperforms the existing BUDA approaches in terms of adaptation performance and robustness.