An analysis of modeling and training decisions for greener computer vision systems

Rey Juárez, Santiago del

View/Open

173116.pdf (3,712Mb) (Restricted access)

View UPCommons Usage Statistics

LA Referencia / Recolecta stats

Cita com:

Show full item record

Rey Juárez, Santiago del

Tutor / directorMartínez Fernández, Silverio Juan

; Franch Gutiérrez, Javier

Document typeMaster thesis

Date2023-01-26

Rights accessRestricted access - confidentiality agreement

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder

Abstract

The main goal of this study is to analyze the impact of the model architecture and training strategy when building green computer vision systems. We divide this goal into two research questions. In the first one, we analyze the impact of the model architecture on achieving greener models while keeping accuracy at optimal levels. In the second one, we study the influence of training strategy on producing greener systems.

SubjectsComputer vision, Visió per ordinador

DegreeMÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2017)

URIhttp://hdl.handle.net/2117/385000

Collections

Màsters oficials - Master in Artificial Intelligence - MAI [300]

View UPCommons Usage Statistics

Show full item record

Files	Description	Size	Format	View
173116.pdf		3,712Mb	PDF	Restricted access

UPCommons. Global access to UPC knowledge

An analysis of modeling and training decisions for greener computer vision systems

View/Open

Browse