ProCAP：面向视觉-语言模型的概率交叉注意力提示学习
原标题：ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models
AI 摘要
该论文提出 ProCAP，一种用于视觉-语言模型（如 CLIP）的概率化交叉注意力提示学习框架。它学习视觉与文本提示 token，并通过堆叠的双向多头交叉注意力让两个分支相互精炼，同时用高斯均值与方差参数化提示 token 并加入 KL 正则，以缓解少样本下的过拟合。在 11 个数据集的少样本 base-to-novel 泛化、跨数据集迁移和 ImageNet 域泛化基准上，ProCAP 在保持 CLIP 主干冻结的情况下取得较强的综合性能。
正文节选
ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision–Language ModelsThanks: Generative AI tools were used to assist with LaTeX formatting, language revision, and consistency checks of literature tables. The authors verified all citations, numerical results, scientific claims, and final content and take full responsibility for the manuscript. Abstract Pre-trained vision–language models such as CLIP can recognize new categories via prompting, but they often struggle when labeled data a