Review of large vision models and visual prompt engineering
Обзор больших зрительных моделей и визуальной инженерии промптов
2023-11-01
SCID: 54.1/nd7sjvdx
Discuss with AI
artificial general intelligencecomputer visionlarge vision modelsvisual prompt engineeringvisual tasks
Figures from the paper
Abstract (AI)
Visual prompt engineering is a fundamental methodology in the field of visual and image artificial general intelligence. As the development of large vision models progresses, the importance of prompt engineering becomes increasingly evident. Designing suitable prompts for specific visual tasks has emerged as a meaningful research direction. This review aims to summarize the methods employed in the computer vision domain for large vision models and visual prompt engineering, exploring the latest advancements in visual prompt engineering. We present influential large models in the visual domain and a range of prompt engineering methods employed on these models. It is our hope that this review provides a comprehensive and systematic description of prompt engineering methods based on large visual models, offering valuable insights for future researchers in their exploration of this field.
Key Findings
1
The growing capabilities of large vision models are increasing the importance of designing task-specific visual prompts.
2
The paper provides a comprehensive and systematic overview of recent visual prompt-engineering advances to support future research.
3
The review summarizes influential large vision models and the prompt-engineering methods used with them in computer vision.
4
Visual prompt engineering is identified as a fundamental methodology for visual and image artificial general intelligence.
Research Object
large vision models and visual prompt engineering methods in computer vision
Research Subject
methods, applications, and recent advances of visual prompt engineering for specific visual tasks
Publication Details
Publication Date
2023-11-01
Journal
Publisher
ISSN
Cited by
218
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai14
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer2019
LLaMA: Open and Efficient Foundation Language Models2023
A Survey of Large Language Models2026
Swin Transformer V2: Scaling Up Capacity and Resolution2022
On the Opportunities and Risks of Foundation Models2021
PaLM: Scaling Language Modeling with Pathways2022
An Empirical Study of Training Self-Supervised Vision Transformers2021
Flamingo: a Visual Language Model for Few-Shot Learning2022
Decoupled Knowledge Distillation2022
Transformer in Transformer2021
Deep learning, reinforcement learning, and world models2022
Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper)2023