C-DGPA: Class-Centric Dual-Alignment Generative Prompt Adaptation

TL;DR

C-DGPA introduces a dual-branch approach for unsupervised domain adaptation in vision-language models, effectively aligning both marginal and conditional distributions to improve semantic discriminability and domain invariance.

Contribution

It proposes a novel dual alignment framework with a Class Mapping Mechanism to better align distributions and enhance prompt adaptation in domain adaptation tasks.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Effectively aligns marginal and conditional distributions.

Improves semantic discriminability in domain adaptation.

Abstract

Unsupervised Domain Adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. Directly deploying Vision-Language Models (VLMs) with prompt tuning in downstream UDA tasks faces the signifi cant challenge of mitigating domain discrepancies. Existing prompt-tuning strategies primarily align marginal distribu tion, but neglect conditional distribution discrepancies, lead ing to critical issues such as class prototype misalignment and degraded semantic discriminability. To address these lim itations, the work proposes C-DGPA: Class-Centric Dual Alignment Generative Prompt Adaptation. C-DGPA syner gistically optimizes marginal distribution alignment and con ditional distribution alignment through a novel dual-branch architecture. The marginal distribution alignment branch em ploys a dynamic adversarial training framework to bridge marginal distribution discrepancies. Simultaneously, the con ditional distribution alignment branch introduces a Class Mapping Mechanism (CMM) to align conditional distribu tion discrepancies by standardizing semantic prompt under standing and preventing source domain over-reliance. This dual alignment strategy effectively integrates domain knowl edge into prompt learning via synergistic optimization, ensur ing domain-invariant and semantically discriminative repre sentations. Extensive experiments on OfficeHome, Office31, and VisDA-2017 validate the superiority of C-DGPA. It achieves new state-of-the-art results on all benchmarks.