Few-shot image classification based on transfer learning and data enhancement

Yawen Sun

doi:10.1117/12.3044868

9 October 2024 Few-shot image classification based on transfer learning and data enhancement

Yawen Sun

Proceedings Volume 13288, Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024); 132880Q (2024) https://doi.org/10.1117/12.3044868
Event: Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024), 2024, Chengdu, China

Abstract

The task of few-shot image classification involves dividing a large number of unknown label samples using only a limited number of known label samples. Previous approaches commonly incorporated an efficient initial embedding network into the meta-learning process, which significantly influenced model performance. However, these methods fail to address the issue of overfitting in few-shot learning (FSL) due to the scarcity of available data. Traditional convolutional neural networks also struggle to effectively extract information from such limited samples. Therefore, this paper proposes the introduction of AmdimNet as an embedded network that maximizes mutual information among samples, enabling it to capture detailed feature information from each individual sample within this constrained setting. Additionally, we perform simple data augmentation on the support set to increase its size and mitigate overfitting occurrences. Finally, we adopt a suitable evaluation metric to enhance classification accuracy. Experimental results demonstrate significant improvements achieved by our proposed method on mainstream few-shot image classification benchmark datasets.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yawen Sun "Few-shot image classification based on transfer learning and data enhancement", Proc. SPIE 13288, Fourth International Conference on Computer Graphics, Image, and Virtualization (ICCGIV 2024), 132880Q (9 October 2024); https://doi.org/10.1117/12.3044868

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
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Feature extraction

Image classification

Machine learning

Semantics

Solid state lighting

Statistical modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years