视觉语言模型引导的最优传输无源域自适应
Vision-Language Model Guided Source-Free Domain Adaptation via Optimal Transport
用预训练 VLM 的语义先验替代不可靠伪标签来构造目标特征与源原型的 OT 匹配，并配合模型↔VLM 双向蒸馏交替训练，可作为无源域自适应、测试时无标签迁移场景下替代伪标签自训练的通用范式。
原文依据 leverages a pretrained Vision-Language Model (VLM) to guide optimal transport (OT) alignment between target features and source prototypes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无监督域自适应将知识从有标注源域迁移到无标注目标域。当源数据无法获取时，无源域自适应（SFDA）成为一种实用的替代方案。然而，现有 SFDA 方法主要依赖基于伪标签的自训练，在域间差异较大时往往会累积噪声与偏差。我们提出 VSFOT，一个利用预训练视觉语言模型（VLM）引导目标特征与源原型之间最优传输（OT）对齐的框架。VSFOT 不依赖不可靠的伪标签，而是采用由 VLM 导出的语义先验与基于 OT 的匹配策略，实现稳定可靠的适配。为进一步增强域对齐，VSFOT 引入双向蒸馏机制：模型从 VLM 学习语义一致性，同时 VLM 利用模型提供的任务特定线索得到改进。这两个阶段在训练过程中交替进行。通过结合 VLM 的泛化能力与任务模型的判别能力，VSFOT 实现了鲁棒的无源适配，并在四个基准数据集上持续优于现有 SFDA 方法。代码已公开。
英文原文摘要 1217 字符
Unsupervised domain adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. When source data cannot be accessed, source-free domain adaptation (SFDA) becomes a practical alternative. However, existing SFDA methods mainly rely on pseudo-label based self-training, which often accumulates noise and bias under large domain gaps. We propose VSFOT, a framework that leverages a pretrained Vision-Language Model (VLM) to guide optimal transport (OT) alignment between target features and source prototypes. Instead of relying on unreliable pseudo-labels, VSFOT employs VLM-derived semantic priors and an OT-based matching strategy to achieve stable and reliable adaptation. To further enhance domain alignment, VSFOT incorporates a bidirectional distillation mechanism in which the model learns semantic consistency from the VLM, while the VLM is refined using task-specific cues from the model. These two stages alternate during training. By combining the generalization ability of the VLM with the discriminative power of the task model, VSFOT achieves robust, source-free adaptation and consistently outperforms existing SFDA methods on four benchmark datasets. The code is available.