English

Supervised Fine-tuning in turn Improves Visual Foundation Models

Computer Vision and Pattern Recognition 2024-04-12 v2 Artificial Intelligence

Abstract

Image-text training like CLIP has dominated the pretraining of vision foundation models in recent years. Subsequent efforts have been made to introduce region-level visual learning into CLIP's pretraining but face scalability challenges due to the lack of large-scale region-level datasets. Drawing inspiration from supervised fine-tuning (SFT) in natural language processing such as instruction tuning, we explore the potential of fine-grained SFT in enhancing the generation of vision foundation models after their pretraining. Thus a two-stage method ViSFT (Vision SFT) is proposed to unleash the fine-grained knowledge of vision foundation models. In ViSFT, the vision foundation model is enhanced by performing visual joint learning on some in-domain tasks and then tested on out-of-domain benchmarks. With updating using ViSFT on 8 V100 GPUs in less than 2 days, a vision transformer with over 4.4B parameters shows improvements across various out-of-domain benchmarks including vision and vision-linguistic scenarios.

Keywords

Cite

@article{arxiv.2401.10222,
  title  = {Supervised Fine-tuning in turn Improves Visual Foundation Models},
  author = {Xiaohu Jiang and Yixiao Ge and Yuying Ge and Dachuan Shi and Chun Yuan and Ying Shan},
  journal= {arXiv preprint arXiv:2401.10222},
  year   = {2024}
}

Comments

23 pages, 3 figures, Project page: https://github.com/TencentARC/ViSFT/tree/main

R2 v1 2026-06-28T14:20:46.355Z