Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark
International Journal of Computer Vision · 2026-06 · 134 (6)
DOI: 10.1007/s11263-026-02864-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 03.06.2026. Verfasst von Yi Xin und 14 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 243 Literaturangaben.
Abstract (Originalsprache)
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 and the benchmark codebase are available at https://github.com/synbol/Awesome-Parameter-Efficient-Transfer-Learning.
Zitieren
APA
Xin, Y., Yang, J., Luo, S., Du, Y., Qin, Q., Chen, H., Cen, K., He, Y., Fu, B., Cao, Y., He, J., Yang, X., Zhai, G., Yang, M., & Liu, X. (2026). Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark. International Journal of Computer Vision, 134(6). https://doi.org/10.1007/s11263-026-02864-6
Vancouver
Xin Y, Yang J, Luo S, Du Y, Qin Q, Chen H, et al. Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark. International Journal of Computer Vision. 2026;134(6). doi:10.1007/s11263-026-02864-6
BibTeX
@article{Xin2026,
author = {Xin, Yi and Yang, Jianjiang and Luo, Siqi and Du, Yuntao and Qin, Qi and Chen, Haoxing and Cen, Kangrui and He, Yangfan and Fu, Bin and Cao, Yuewen and He, Junjun and Yang, Xiaokang and Zhai, Guangtao and Yang, Ming-Hsuan and Liu, Xiaohong},
title = {Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark},
journal = {International Journal of Computer Vision},
year = {2026},
volume = {134},
number = {6},
doi = {10.1007/s11263-026-02864-6}
}
EUVIMED