AI RESEARCH
Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment
arXiv CS.LG
•
ArXi:2605.15720v1 Announce Type: cross Medical referring image segmentation (MRIS) requires pixel-level masks aligned with textual descriptions of anatomical locations, making annotation costly in low-label regimes. Semi-supervised learning (SSL) can mitigate this burden by leveraging unlabeled data, but its success hinges on maintaining reliable image-text alignment under perturbations.