Proposing an Efficient CNN-Based Architecture for Image Processing

doi:10.1007/978-3-032-15984-7_26

Proposing an Efficient CNN-Based Architecture for Image Processing

2026-01-01

0

PRE

AI

V

Verner Rafael Ferreira *

A

Anne M. P. Canuto

DOI：10.1007/978-3-032-15984-7_26

Original

Original request for help

Save

Abstract

En 中文

This paper introduces the Defiber layer, a Convolutional Neural Network (CNN) architecture component that systematically reduces input size during the convolution phase. In order to assess the feasibility of the proposed model, an empirical analysis was conducted using two image datasets: the CIFAR-10 dataset and an additional in-house dataset. Aiming to provide a comprehensive comparison, several existing CNN architectures are also included in this empirical analysis. The models are assessed based on accuracy and hardware performance criteria, including inference time and throughput. Our model surpasses expectations, outperforming some of the other evaluated models, both deep and mobile. Notably, the Defiber layer demonstrates remarkable effectiveness and consistent results during performance tests.

Keywords:

CNN

down sampling

image classification

Proposing an Efficient CNN-Based Architecture for Image Processing

Abstract

Journal

Organization