Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these models scale to billions or even trillions of parameters, conventional full fine-tuning has become increasingly impractical due to its high computational and storage demands. To address these challenges, parameter-efficient fine-tuning (PEFT) has emerged as a promising alternative, aiming to achieve performance comparable to full fine-tuning while making minimal adjustments to the model parameters. This paper presents a comprehensive survey of the latest advancements in the visual PEFT field, systematically reviewing current methodologies and categorizing them into four primary categories: addition-based, partial-based, unified-based, and multi-task tuning. In addition, this paper offers an in-depth analysis of widely used visual datasets and real-world applications where PEFT methods have been successfully applied. Furthermore, this paper introduces the V-PEFT Bench, a unified benchmark designed to standardize the evaluation of PEFT methods across a diverse set of vision tasks, ensuring consistency and fairness in comparison. Finally, the paper outlines potential directions for future research to propel advances in the PEFT field. A comprehensive collection of resources is available at https://github.com/synbol/Awesome-Parameter-Efficient-Transfer-Learning.
@article{arxiv.2402.02242,
title = {Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark},
author = {Yi Xin and Jianjiang Yang and Siqi Luo and Yuntao Du and Qi Qin and Kangrui Cen and Yangfan He and Zhiwei Zhang and Bin Fu and Xiaokang Yang and Guangtao Zhai and Ming-Hsuan Yang and Xiaohong Liu},
journal= {arXiv preprint arXiv:2402.02242},
year = {2025}
}