Normalized determinant pooling layer in CNNs for multi-label classification

Alessandro Giuliano; Waleed Hilal; Naseem Alsadi; John Yawney; S. Andrew Gadsden

doi:10.1117/12.2663916

19 July 2023 Normalized determinant pooling layer in CNNs for multi-label classification

Alessandro Giuliano, Waleed Hilal, Naseem Alsadi, John Yawney, S. Andrew Gadsden

Proceedings Volume 12523, Computational Imaging VII ; 1252309 (2023) https://doi.org/10.1117/12.2663916
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Convolutional neural networks (CNNs) are a widely researched neural network architecture that has demonstrated exemplary performance in image processing tasks and applications compared to other popular deep learning and machine learning methods resulting in state-of-the-art performance in many image processing tasks such as image classification and segmentation. CNNs operate on the principle of automated learning of filters or kernels in contrast with hand-crafted digital filters to extrapolate features from images effectively. This paper aims to investigate whether a matrix's determinant can be used to preserve information in CNN convolutional layers. Geometrically the absolute value of the determinant is defined as a scaling factor of the linear transformation resulting from matrix multiplication. When an image's size is reduced into a feature space through a convolutional layer of a CNN, some information is lost. The intuition is that the scaling factor that results from the determinant of the pooling layer matrix can enhance the feature space introducing scaling as a piece of information in the feature space as well as lost relations between adjacent pixels.

Conference Presentation

Citation Download Citation

Alessandro Giuliano, Waleed Hilal, Naseem Alsadi, John Yawney, and S. Andrew Gadsden "Normalized determinant pooling layer in CNNs for multi-label classification", Proc. SPIE 12523, Computational Imaging VII , 1252309 (19 July 2023); https://doi.org/10.1117/12.2663916

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