Linear Approximation in Frequency Domain
Reducing Line Loss
Improving Translational Accuracy
Convolution Properties I
Downsampling
Convolution Properties II
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Jun 3, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
R Aiudi1,2, R Pacelli3, P Baglioni4
1Dipartimento di Scienze Matematiche, Fisiche e Informatiche, Università degli Studi di Parma, Parma, Italy.
Convolutional neural networks (CNNs) show superior performance in finite-width settings due to local kernel renormalization, unlike fully-connected networks. This mechanism enables feature learning in shallow CNNs, a capability absent in fully-connected architectures.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: