Downsampling
Upsampling
Deconvolution
Reducing Line Loss
Convolution: Math, Graphics, and Discrete Signals
Convolution Properties II
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Dec 29, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
1School of Data Science and Department of Mathematics, City University of Hong Kong, Kowloon, Hong Kong.
Deep convolutional neural networks (CNNs) show promise for approximating complex functions and learning data manifold features. Downsampling techniques enable theoretical analysis, demonstrating CNNs match fully-connected network capabilities.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: