Utilizando la moda para adultos para mejorar el reconocimiento de la moda infantil = Leveraging adult fashion to enhance children’s fashion recognition

Igareta Herraiz, Ángel Luis (2021). Utilizando la moda para adultos para mejorar el reconocimiento de la moda infantil = Leveraging adult fashion to enhance children’s fashion recognition. Thesis (Master thesis), E.T.S. de Ingenieros Informáticos (UPM).

Description

Title: Utilizando la moda para adultos para mejorar el reconocimiento de la moda infantil = Leveraging adult fashion to enhance children’s fashion recognition
Author/s:
  • Igareta Herraiz, Ángel Luis
Contributor/s:
  • Björkman, Mårten
  • Paraíso Medina, Sergio
Item Type: Thesis (Master thesis)
Masters title: Data Science
Date: June 2021
Subjects:
Freetext Keywords: CNN, Machine learning, Transfer learning, Fashion analysis, Children’s fashion, Clothing attribute recognition
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (3MB) | Preview

Abstract

The future of the fashion industry is expected to be online, thus a significant amount of research is being conducted in the field of fashion image analysis. Currently, a task that places a heavy workload on online stores is manually tagging new garments, including attributes such as category, color, pattern, or style. To this end, extensive research has targeted the automatic prediction of clothing categories and attributes, achieving promising results. Nevertheless, no previous study has been found in the literature that specifically reflects the performance of clothing attribute recognition with children’s clothing. This work intends to fill this gap and effectively present, in the same fashion analysis task, how a model trained in adult fashion performs over a model trained exclusively in children’s fashion. When examining the global understanding of children’s fashion apparel, the experiments exhibit that the best performance is obtained when leveraging the domain knowledge of adult fashion, specifically from the iMaterialist dataset, wherein the best model a difference in the overall performance of about 3% was achieved compared to pre¬training on the ImageNet dataset or 12% when only children’s fashion was considered for training.

More information

Item ID: 69115
DC Identifier: https://oa.upm.es/69115/
OAI Identifier: oai:oa.upm.es:69115
Deposited by: Biblioteca Facultad de Informatica
Deposited on: 23 Nov 2021 14:32
Last Modified: 23 Nov 2021 14:32
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM