Fine-graded image classification network based on Faster MMAL-Net

Ke Han; Xiu Ji; Beimin Xie; Yong Wang; Shuai Gao

doi:10.1117/12.2671512

29 March 2023 Fine-graded image classification network based on Faster MMAL-Net

Ke Han, Xiu Ji, Beimin Xie, Yong Wang, Shuai Gao

Proceedings Volume 12594, Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022); 125941N (2023) https://doi.org/10.1117/12.2671512
Event: Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022), 2022, Xi'an, China

Abstract

In the fine-grained image classification task, the huge intra class variance determines that the classification of the task depends on coarse-grained and fine-grained information. However, there is still a lack of research on how to quickly and effectively fuse multi granularity features. Therefore, this paper proposes a fine-grained image classification network based on fast MMAL net and studies the impact on the classification accuracy and convergence speed of fine-grained classification network. The fast aolm module is used to predict the position of the object, and the fast APPM module is used to predict the information of the key areas of the object without the need for bounding boxes or labels. The method proposed in this paper achieves high accuracy on the three data sets of Stanford cars cub-200-2011, fgvc aircraft and Stanford cars respectively, which shows that this method can obtain excellent classification performance.

Citation Download Citation

Ke Han, Xiu Ji, Beimin Xie, Yong Wang, and Shuai Gao "Fine-graded image classification network based on Faster MMAL-Net", Proc. SPIE 12594, Second International Conference on Electronic Information Engineering and Computer Communication (EIECC 2022), 125941N (29 March 2023); https://doi.org/10.1117/12.2671512

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