Tell2Adapt：通过视觉基础模型实现源无关无监督领域自适应的统一框架
Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model
AI总结：
Tell2Adapt通过视觉基础模型实现源无关无监督领域自适应，利用上下文感知提示正则化和视觉合理性细化提升医学图像分割性能。
摘要：
源无关无监督领域自适应（SFUDA）对于在多样化临床环境中部署深度学习模型至关重要。然而，现有方法通常针对低差距、特定领域转移设计，无法推广到统一、多模态和多目标的框架，这成为实际应用的主要障碍。为了解决这一问题，我们引入了Tell2Adapt，一种新的SFUDA框架，利用视觉基础模型（VFM）的广泛通用知识。我们的方法通过上下文感知提示正则化（CAPR）确保高保真VFM提示，将各种文本提示稳健地转换为标准指令。这使得能够生成高质量的伪标签，以高效地将轻量级学生模型适应到目标领域。为了保证临床可靠性，该框架整合了视觉合理性细化（VPR），利用VFM的解剖学知识，将适应模型的预测重新定位到目标图像的低级视觉特征中，有效去除噪声和假阳性。我们进行了迄今为止最全面的SFUDA评估，验证了我们的框架在10种领域适应方向和22种解剖学目标上的有效性，包括脑、心脏、息肉和腹部目标。我们的结果表明，Tell2Adapt在统一的SFUDA框架中始终优于现有方法，在医学图像分割中实现了SOTA。代码可在https://github.com/derekshiii/Tell2Adapt上获取。
英文摘要：
Source Free Unsupervised Domain Adaptation (SFUDA) is critical for deploying deep learning models across diverse clinical settings. However, existing methods are typically designed for low-gap, specific domain shifts and cannot generalize into a unified, multi-modalities, and multi-target framework, which presents a major barrier to real-world application. To overcome this issue, we introduce Tell2Adapt, a novel SFUDA framework that harnesses the vast, generalizable knowledge of the Vision Foundation Model (VFM). Our approach ensures high-fidelity VFM prompts through Context-Aware Prompts Regularization (CAPR), which robustly translates varied text prompts into canonical instructions. This enables the generation of high-quality pseudo-labels for efficiently adapting the lightweight student model to target domain. To guarantee clinical reliability, the framework incorporates Visual Plausibility Refinement (VPR), which leverages the VFM's anatomical knowledge to re-ground the adapted model's predictions in target image's low-level visual features, effectively removing noise and false positives. We conduct one of the most extensive SFUDA evaluations to date, validating our framework across 10 domain adaptation directions and 22 anatomical targets, including brain, cardiac, polyp, and abdominal targets. Our results demonstrate that Tell2Adapt consistently outperforms existing approaches, achieving SOTA for a unified SFUDA framework in medical image segmentation. Code are avaliable at https://github.com/derekshiii/Tell2Adapt.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
