A novel design of learnable pooling algorithm

Songsong Feng; Binjun Wang

doi:10.1117/12.2660788

2 February 2023 A novel design of learnable pooling algorithm

Songsong Feng, Binjun Wang

Proceedings Volume 12462, Third International Symposium on Computer Engineering and Intelligent Communications (ISCEIC 2022); 1246230 (2023) https://doi.org/10.1117/12.2660788
Event: International Symposium on Computer Engineering and Intelligent Communications (ISCEIC 2022), 2022, Xi'an, China

Abstract

Pooling is an important part of modern convolutional neural networks, which can expand the perception field, reduce the parameter matrix, and avoid overfitting. Currently used maximum pooling, average pooling and various subsequent improved pooling algorithms cannot take into account the contour and background information of the feature map at the same time. In addition, the performance of different pooling algorithms varies greatly on different models and datasets. In this paper, we propose a learnable pooling algorithm. The introduction of learnable parameters allows the pooling layer to adaptively optimize the selection of key feature information that is beneficial to improve model performance during model training. It is experimentally verified that the pooling algorithm has superior performance over the existing maximum pooling and average pooling on several classical models and public datasets for image classification and text classification. The pooling algorithm with the introduction of learnable parameters can better prevent overfitting, steadily improve the accuracy of the model, and is highly generalizable.

Citation Download Citation

Songsong Feng and Binjun Wang "A novel design of learnable pooling algorithm", Proc. SPIE 12462, Third International Symposium on Computer Engineering and Intelligent Communications (ISCEIC 2022), 1246230 (2 February 2023); https://doi.org/10.1117/12.2660788

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

Image classification

Convolutional neural networks

Performance modeling

Image segmentation

Process modeling

Visual process modeling

Evolutionary algorithms

Show All Keywords

Keywords/Phrases

Search In:

Publication Years