MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image SegmentationDate: 2026-02-27Fetched: 2026-02-28T01:46:38.376518+00:00AuthorsTaha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari, Berardino Barile, Yiming Xiao, Hassan RivazLinksHFarXivPDFGitHub2Abstract中文摘要EnglishMedCLIPSeg 利用 patch 级嵌入和概率注意力将 CLIP 适配于医学图像分割，实现了数据高效、不确定性感知且具备可解释性的分割。
