A novel meta-transfer learning model with attention mechanism for insect classification

Daohong Zhang; Jiangtao Hu; Surui Liu; Yuqiang Hu; Jielei Chu

doi:10.1117/12.3011536

7 December 2023 A novel meta-transfer learning model with attention mechanism for insect classification

Daohong Zhang, Jiangtao Hu, Surui Liu, Yuqiang Hu, Jielei Chu

Author Affiliations +

Proceedings Volume 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023); 129415D (2023) https://doi.org/10.1117/12.3011536
Event: Third International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 203), 2023, Yinchuan, China

Abstract

This paper proposes a novel meta-transfer learning model, ATN-MTL, which incorporates the attention mechanism into meta-transfer learning for insect classification. The attention mechanism allows the ATN-MTL model to focus on specific regions of the input data during the learning and training process. Hence, it has capability to enhance the model’s feature extraction performance. Furthermore, a novel insect specimen dataset is presented in this paper for the first time. Experimental results demonstrate that the ATN-MTL model achieves classification accuracies of 97.99% and 98.94% in the five-way (five-shot) and five-way (ten-shot) scenarios on this novel dataset, respectively. Compared to the model without the attention mechanism, the attention mechanism improves the classification performance of the ATN-MTL model. The experimental results also confirm that the first CAM and then SAM strategy among the three CBAM strategies performs the best performance.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Daohong Zhang, Jiangtao Hu, Surui Liu, Yuqiang Hu, and Jielei Chu "A novel meta-transfer learning model with attention mechanism for insect classification", Proc. SPIE 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), 129415D (7 December 2023); https://doi.org/10.1117/12.3011536

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

Content addressable memory

Education and training

Data modeling

Performance modeling

Feature extraction

Deep learning

Machine learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years