Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model

TL;DR

Tell2Adapt is a novel source-free unsupervised domain adaptation framework that leverages Vision Foundation Models to improve medical image segmentation across diverse clinical domains with high reliability.

Contribution

It introduces a unified SFUDA framework utilizing Vision Foundation Models with novel prompts regularization and visual plausibility refinement for better generalization and accuracy.

Findings

Outperforms existing methods across 10 domain directions and 22 anatomical targets.

Achieves state-of-the-art results in medical image segmentation.

Validated on diverse clinical datasets including brain, cardiac, and abdominal images.

Abstract

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.