Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models 文章

ArXiv CS.CV2026-05-27NEWSen作者: Yuanwei Hu, Bo Peng, Yadan Luo, Zhen Fang, Ling Chen, Jie Lu
大语言模型
查看原文 →
关系图谱

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models · 相关技术

相关技术

ginODElanguage modelzero-shotprompt engineeringmachine learningSSEReferring expression comprehension (REC)PromptParts-of-Speech (POS) tagsNarrative Abstraction BenchmarkNPUNATVision-Language ModelsVLMHISGranular Alignment ParadigmEvaluation Driven DevelopmentENAANNMac