Visual recognition incorporating features of self-supervised models for the use of unlabelled data

Vista sencilla de ítem
dc.contributor.advisorPeralta Márquez, Billy
dc.contributor.advisorNicolis, Orietta
dc.contributor.authorDíaz Calderón, Gabriel Antonio
dc.contributor.editorFacultad de Ingeniería
dc.date.accessioned2023-01-16T21:11:40Z
dc.date.available2023-01-16T21:11:40Z
dc.date.issued2021
dc.descriptionTesis (Magíster en Ciencias de la Computación)es
dc.description.abstractAutomatic visual object recognition has gained great popularity in the world and is successfully applied to various areas such as robotics, security or commerce using deep learning techniques. Training in machine learning models based on deep learning requires an enormous amount of supervised data, which is expensive to obtain. An alternative is to use semi-supervised models as co-training where the views given by deep networks are differentiated using models that incorporate lateral information from each training object. In this document, we describe and test a co-training model for deep networks, adding as auxiliary inputs to self-supervised network features. The results show that the proposed model managed to converge using a few dozen iterations, exceeding 2 % in precision compared to recent models. This model, despite its simplicity, manages to be competitive with more complex recent works. As future work, we plan to modify deep self-supervised networks to increase diversity in co-training learning.es
dc.identifier.urihttps://repositorio.unab.cl/xmlui/handle/ria/36154
dc.language.isoeses
dc.publisherUniversidad Andrés Belloes
dc.subjectRedes Neurales (Ciencia de la Computación)es
dc.subjectAlgoritmos Computacionaleses
dc.titleVisual recognition incorporating features of self-supervised models for the use of unlabelled dataes
dc.typeTesises
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
a140046_Díaz_G_Visual_recognition_incorporating_features_of_2021_Tesis.pdf
Tamaño:
673.13 KB
Formato:
Adobe Portable Document Format
Descripción:
TEXTO COMPLETO EN ESPAÑOL
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
FIng - Trabajos de Titulación Post-Grado