Optimizing binary neural network quantization for fixed pattern noise robustness

Optimizing binary neural network quantization for fixed pattern noise robustness

Abstract This work presents a comprehensive analysis of how extreme data quantization and fixed pattern noise (FPN) from CMOS imagers affect the performance of deep neural networks for image recognition tasks. Binary neural networks (BNN) are particularly attractive for resource-constrained embedded...

Full description

Saved in:
Bibliographic Details
Main Authors: Francisco Javier Andreo-Oliver, Gines Domenech-Asensi, Jose Angel Diaz-Madrid, Ramon Ruiz-Merino, Juan Zapata-Perez
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Deep neural network
Computer vision
Data quantization
Batch normalization
Fixed pattern noise
CMOS imagers
Online Access:https://doi.org/10.1038/s41598-025-10833-1
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-025-10833-1

Similar Items