Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?Date: 2026-02-27Fetched: 2026-02-28T01:46:58.748014+00:00AuthorsTilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos ToliasLinksHFarXivPDFGitHub4Abstract中文摘要English检索增强的测试时自适应通过文本与视觉特征的学习融合，弥合了零样本与有监督开放词汇分割之间的性能差距。
