Few-shot image recognition based on improved Siamese neural network

Pengsong Li; Zhiyi Ji; Bingqian Zhou

doi:10.1117/12.3037880

12 September 2024 Few-shot image recognition based on improved Siamese neural network

Pengsong Li, Zhiyi Ji, Bingqian Zhou

Author Affiliations +

Proceedings Volume 13256, Fourth International Conference on Computer Vision and Pattern Analysis (ICCPA 2024); 132560X (2024) https://doi.org/10.1117/12.3037880
Event: Fourth International Conference on Computer Vision and Pattern Analysis (ICCPA 2024), 2024, Anshan, China

Abstract

To solve the problems caused by insufficient training samples in few-shot image recognition, such as low accuracy and slow speed, an improved siamese network model is designed in the paper. Based on peculiar siamese networks, this paper selects lightweight convolutional neural network MobileNet V2 which is pretrained by transfer learning as the feature extraction part. Meanwhile, a new activation function is designed in this paper. The results of comparative experiments show that the improved siamese neural network can enhance the speed and accuracy of recognition for few-shot datasets.

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

Citation Download Citation

Pengsong Li, Zhiyi Ji, and Bingqian Zhou "Few-shot image recognition based on improved Siamese neural network", Proc. SPIE 13256, Fourth International Conference on Computer Vision and Pattern Analysis (ICCPA 2024), 132560X (12 September 2024); https://doi.org/10.1117/12.3037880

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