English

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

Computer Vision and Pattern Recognition 2025-03-17 v2

Abstract

Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning a tiny set of context vectors. Nevertheless, in this work, we reveal that freezing the parameters of VLMs during learning the context vectors neither facilitates the transferability of pre-trained knowledge nor improves the memory and time efficiency significantly. Upon further investigation, we find that reducing both the length and width of the feature-gradient propagation flows of the full fine-tuning (FT) baseline is key to achieving effective and efficient knowledge transfer. Motivated by this, we propose Skip Tuning, a novel paradigm for adapting VLMs to downstream tasks. Unlike existing PT or adapter-based methods, Skip Tuning applies Layer-wise Skipping (LSkip) and Class-wise Skipping (CSkip) upon the FT baseline without introducing extra context vectors or adapter modules. Extensive experiments across a wide spectrum of benchmarks demonstrate the superior effectiveness and efficiency of our Skip Tuning over both PT and adapter-based methods. Code: https://github.com/Koorye/SkipTuning.

Keywords

Cite

@article{arxiv.2412.11509,
  title  = {Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves},
  author = {Shihan Wu and Ji Zhang and Pengpeng Zeng and Lianli Gao and Jingkuan Song and Heng Tao Shen},
  journal= {arXiv preprint arXiv:2412.11509},
  year   = {2025}
}
R2 v1 2026-06-28T20:36:32.465Z