MDRAN: a multi-source dual-refining adaptation network for source-free domain adaptation guided by vision-language-model
Source-Free Domain Adaptation (SFDA) adapts a pre-trained source model to an unlabeled target domain without accessing source data, alleviating the need for direct access to source data during adaptation, which reduces the risk of data transmission. Existing methods leverage pre-trained Vision-Language (ViL) models to...