Feature filtering module of convolutional neural networks for image recognition system

Shining Chen; Xianghua Ma

doi:10.1117/12.2673212

14 April 2023 Feature filtering module of convolutional neural networks for image recognition system

Shining Chen, Xianghua Ma

Author Affiliations +

Proceedings Volume 12613, International Conference on Computer Vision, Application, and Algorithm (CVAA 2022); 1261303 (2023) https://doi.org/10.1117/12.2673212
Event: International Conference on Computer Vision, Application, and Algorithm (CVAA 2022), 2022, Chongqing, China

Abstract

Recent research has shown that attention mechanisms can help convolutional networks train and infer more efficiently and accurately. However, the current attention mechanism mainly focuses on the relationship between global features and ignores the relationship between local features. A Feature Filtering Module (FFM) for convolutional neural networks is proposed in this paper. The FFM module uses attention mechanisms in both spatial and channel dimensions and fuses the attention feature maps of the two branches into a 3D attention feature map to help effective feature information flow more efficiently. Extensive tests on the CIFAR-100, and MS COCO show that FFM improves baseline network performance under various models and tasks, demonstrating FFM's versatility.

Citation Download Citation

Shining Chen and Xianghua Ma "Feature filtering module of convolutional neural networks for image recognition system", Proc. SPIE 12613, International Conference on Computer Vision, Application, and Algorithm (CVAA 2022), 1261303 (14 April 2023); https://doi.org/10.1117/12.2673212

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

Convolution

Tunable filters

Convolutional neural networks

Performance modeling

Image classification

Ablation

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years