Supervised Fine-tuning in turn Improves Visual Foundation Models

TL;DR

This paper demonstrates that supervised fine-tuning (SFT) significantly enhances large vision foundation models' performance on diverse out-of-domain tasks, inspired by NLP instruction tuning.

Contribution

Introduces ViSFT, a two-stage supervised fine-tuning method that improves vision foundation models post-pretraining using in-domain visual tasks.

Findings

ViSFT improves performance on out-of-domain benchmarks

Fine-tuning enhances vision and vision-linguistic tasks

Efficient training on large models within 2 days

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.