不依赖源模型，仅用视觉语言模型就能实现高效域适应。
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
- 从零开始训练，仅靠视觉语言模型和目标域无标签数据
- 在Office-Home等三个数据集上性能媲美甚至超越传统方法
- 适合追求真正无源数据依赖的工业级模型部署场景
源域自适应（SFDA）在不访问源数据的前提下将源模型迁移到目标域，解决了隐私与传输问题。然而现有方法仍需基于预训练的源模型初始化，无法真正实现源自由。我们观察到：同一目标域下，不同源模型带来的最终结果差异极小，说明源模型影响有限。为此提出纯视觉语言模型引导的域适应（VODA），完全摆脱对源域的依赖，仅使用随机初始化模型、视觉语言模型和无标签目标数据。分析其适应动态后，提出两阶段去噪区域蒸馏（TS-DRD）：第一阶段用视觉语言模型指导模型预热；第二阶段寻找视觉语言模型与待适应模型共有的去噪区域，提供更干净的监督信号。在Office-Home、VisDA和DomainNet-126上的实验表明，该设置下TS-DRD性能达到或超过现有依赖源模型的SFDA方法，验证了其有效性及VODA设定的潜力。
原文摘要 · Abstract (English)
Source-Free Domain Adaptation (SFDA) adapts source models to target domains without accessing source data, addressing privacy and transmission issues. However, existing methods still initialize from a source pre-trained model and thus are not truly source-free. Recent works have introduced Vision-Language (ViL) models to guide the adaptation process, in these methods, we observe that for the same target domain, different source models yield minimal variation in final results, indicating the source model itself has limited impact. Motivated by this, we propose ViL-Only Domain Adaptation (VODA) , a stricter setting that eliminates all dependencies on source domain, relying solely on a randomly initialized model, a ViL model, and unlabeled target data. We analyze the adaptation dynamics of VODA and introduce Two-Stage Denoised-Region Distillation (TS-DRD) , a two-stage framework that first warms up the model with ViL guidance, then seek a Denoised-Region inherent in both the ViL and adapting model, yielding cleaner supervision for distillation. Experiments on Office-Home, VisDA, and DomainNet-126 show that under VODA, TS-DRD achieves competitive or superior performance to existing SFDA methods that still use source models, demonstrating its effectiveness and the potential of the VODA setting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。