PDbDa: Prompt-tuned dual-branch framework for unsupervised domain adaptation

• PDbDa integrates prompt learning and dual-branch design for robust domain adaptation. • The foundation branch use hierarchical prompts design and prompt knowledge constraints to enhance class discriminability. • The adaptation branch uses feature libraries and domain-aware feature tuning to align source and target domains. • PDbDa consistently outperforms state-of-the-art UDA and prompt-tuning methods on three benchmarks. Large-scale vision-language models demonstrate excellent performance on downstream tasks. However, they face challenges in unsupervised domain adaptation, particularly when domain shifts and semantic loss occur. Although existing prompt learning methods can decouple task-specific semantics from general knowledge, they face two main issues: (i) ineffective coordination between task-specific and general knowledge, leading to poor class discriminability, and (ii) inability to adequately address the domain shift. To address these challenges, we propose PDbDa, a prompt-tuned dual-branch framework for unsupervised domain adaptation that jointly optimizes learnable prompt vectors. PDbDa introduces two key innovations: (i) a foundation branch with a prompt knowledge constraint to regularize task-specific and pretrained knowledge, addressing class discriminability, and (ii) an adaptation branch with a domain-aware feature tuning block to align source and target domain features, mitigating the domain shift. These two branches function synergistically, improving model accuracy and training efficiency. The experimental results on the Office-Home, VisDA-2017, and DomainNet datasets indicate that PDbDa outperforms conventional prompt tuning and UDA methods by an average of 2.2 %-3 %.