Prompt learning in computer vision: a survey

作     者：Yiming LEI Jingqi LI Zilong LI Yuan CAO Hongming SHAN Yiming LEI;Jingqi LI;Zilong LI;Yuan CAO;Hongming SHAN

作者机构：Shanghai Key Laboratory of Intelligent Information ProcessingSchool of Computer ScienceFudan UniversityShanghai 200438China Institute of Science and Technology for Brain-Inspired IntelligenceFudan UniversityShanghai 200433China MOE Frontiers Center for Brain ScienceFudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired TechnologyShanghai 201210China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2024年第25卷第1期

页      面：42-63页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Project supported by the National Natural Science Foundation of China(Nos.62306075 and 62101136) the China Postdoctoral Science Foundation(No.2022TQ0069) the Natural Science Foundation of Shanghai,China(No.21ZR1403600) the Shanghai Municipal of Science and Technology Project,China(No.20JC1419500) the Shanghai Center for Brain Science and Brain-Inspired Technology,China。 

主　　题：Prompt learning Visual prompt tuning(VPT) Image generation Image classification Artificial intelligence generated content(AIGC) 

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