Supervised Fine-tuning in turn Improves Visual Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xiaohu, Ge, Yixiao, Ge, Yuying, Shi, Dachuan, Yuan, Chun, Shan, Ying
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917636711907328
author Jiang, Xiaohu
Ge, Yixiao
Ge, Yuying
Shi, Dachuan
Yuan, Chun
Shan, Ying
author_facet Jiang, Xiaohu
Ge, Yixiao
Ge, Yuying
Shi, Dachuan
Yuan, Chun
Shan, Ying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10222
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Supervised Fine-tuning in turn Improves Visual Foundation Models
Jiang, Xiaohu
Ge, Yixiao
Ge, Yuying
Shi, Dachuan
Yuan, Chun
Shan, Ying
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Supervised Fine-tuning in turn Improves Visual Foundation Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.10222