MinMAE calibration method for convolutional neural network quantization

This article introduces MinMAE, a novel activation calibration method for Post-Training Quantization (PTQ) that significantly reduces accuracy loss in Convolutional Neural Networks (CNN). Motivated by the need for high-fidelity quantization without costly retraining, MinMAE directly minimizes the Me...

Descripción completa

Detalles Bibliográficos

Autores principales:	Artem Vasilev, Andrey I. Kapitanov, Roman Solovyev, Dmitry Telpukhov, Alexander Stempkovskiy, Alexander Kustov, Viktor Prutyanov, Aleksandr Romanov
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	PeerJ Inc. 2026-03-01
Colección:	PeerJ Computer Science
Materias:	Quantization Object detection Neural network
Acceso en línea:	https://peerj.com/articles/cs-3724.pdf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!