How to make use of pretrained models in few-shot classification

Mingyu Fu; Peng Wang

doi:10.1117/12.2668153

20 April 2023 How to make use of pretrained models in few-shot classification

Mingyu Fu, Peng Wang

Proceedings Volume 12602, International Conference on Electronic Information Engineering and Computer Science (EIECS 2022); 1260217 (2023) https://doi.org/10.1117/12.2668153
Event: International Conference on Electronic Information Engineering and Computer Science (EIECS 2022), 2022, Changchun, China

Abstract

Few-shot learning(FSL) aims to generalize model to novel categoeries by few labelled samples, which is challenging for machine. Large-scaled pretrained models, especially vision transformers achieve excellent performances benefiting from numerous and diverse data. Researchers have exploited pretrained models in few-shot classification by simply updating the whole parameters and finetuning on few samples. In this paper, we explore two methods: vision prompt tuning and a reparameterization method called ‘scaling&&shift’ to leverage pretrained models in few-shot classification. Vision prompt tuning is for vision transformer only and we first evaluate the method in few-shot setting. ‘Scaling&&shift’ is originally applied in convolution neural networks(CNN). We extend it to vision transformer. The two methods are evaluated on standard benchmarks such as miniImageNet, CUB, CIFAR-FS, clipart and sketch. The results show that ‘scaling&&shift’ reaches the same level compared to updating the whole parameters. Vision prompt tuning is 0%~5% lower than updating the whole parameters over five datasets while it has quite smaller amount of parameters updated.

Citation Download Citation

Mingyu Fu and Peng Wang "How to make use of pretrained models in few-shot classification", Proc. SPIE 12602, International Conference on Electronic Information Engineering and Computer Science (EIECS 2022), 1260217 (20 April 2023); https://doi.org/10.1117/12.2668153

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Visual process modeling

Transformers

Data modeling

Performance modeling

Convolution

Lawrencium

Neurons

Show All Keywords

Keywords/Phrases

Search In:

Publication Years