AI RESEARCH

TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation

arXiv CS.CV

ArXi:2511.05782v2 Announce Type: replace Unsupervised domain adaptation for medical image segmentation remains a significant challenge due to substantial domain shifts across imaging modalities, such as CT and MRI. While recent vision-language representation learning methods have shown promise, their potential in UDA segmentation tasks remains underexplored. To address this gap, we propose TCSA-UDA, a Text-driven Cross-Semantic Alignment framework that leverages domain-invariant textual class descriptions to guide visual representation learning. Our approach.