Please use this identifier to cite or link to this item:
Title: Effective Color Spaces for Quaternion-valued Neural Network in Depth Estimation
Authors: Pham, Minh Tuan
Nguyen, An Hung
Hoang, Cao Duy
Keywords: Color-space
Neural networks
Depth estimation
Deep Learning
Issue Date: Jun-2023
Publisher: Vietnam-Korea University of Information and Communication Technology
Series/Report no.: CITA;
Abstract: In the development of deep learning technology, we frequently focus on how to create the best neutral architecture to enhance models and obtain higher accuracy while overlooking a way to speed up training because any parameters are affected by color space. Finding the ideal color space for Quaternion-valued neural network in-depth estimation as survey methods is the focus of this paper. We use a small dataset from the Middlebury dataset [1] to survey training progress in a quaternion-valued neural network that was mentioned in one of our other papers. As a result, we find that HED color-space makes the best training progress in the survey results.
Description: Proceeding of The 12th Conference on Information Technology and It's Applications (CITA 2023); pp: 169-180.
ISBN: 978-604-80-8083-9
Appears in Collections:CITA 2023 (National)

Files in This Item:

 Sign in to read

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.