Prompt learning has attracted broad attention in computer vision since the large pre-trained vision-language models (VLMs) exploded. Based on the close relationship between vision and language information built by VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligence generated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual prompt learning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, we review the vision prompt learning methods and prompt-guided generative models, and discuss how to improve the efficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising research directions concerning prompt learning.

自从大型预训练视觉语言模型（VLM）爆炸式增长以来，即时学习在计算机视觉领域引起了广泛关注。基于 VLM 构建的视觉和语言信息之间的密切关系，即时学习成为人工智能生成内容（AIGC）等许多重要应用中的关键技术。在这项调查中，我们对与 AIGC 相关的视觉提示学习进行了渐进和全面的回顾。我们首先介绍VLM，视觉提示学习的基础。然后，我们回顾了视觉提示学习方法和提示引导生成模型，并讨论了如何提高 AIGC 模型适应特定下游任务的效率。最后，我们提供了一些有关即时学习的有前景的研究方向。