Core Concepts
Exploring off-the-shelf ViL models for Source-Free Domain Adaptation improves adaptation performance significantly.
Stats
Relying on pseudo labeling and/or auxiliary supervision leads to errors in conventional methods.
Extensive experiments show that DIFO significantly outperforms state-of-the-art alternatives.
Quotes
"Directly applying the ViL model to the target domain in a zero-shot fashion is unsatisfactory."
"We propose a novel Distilling multImodal Foundation mOdel (DIFO) approach."