Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • AccederRegistro (usuarios no UPC)Acceder (usuarios no UPC)
  • mailContacto
  • world Castellano 
    • Català
    • Castellano
    • English
  • userInicia sesión   
      AccederRegistro (usuarios no UPC)Acceder (usuarios no UPC)

UPCommons. Portal de acceso abierto al conocimiento de la UPC

57.066 E-prints UPC
You are here:
Ver ítem 
  •   UPCommons
  • E-prints
  • Departaments
  • Departament de Teoria del Senyal i Comunicacions
  • Articles de revista
  • Ver ítem
  •   UPCommons
  • E-prints
  • Departaments
  • Departament de Teoria del Senyal i Comunicacions
  • Articles de revista
  • Ver ítem
JavaScript is disabled for your browser. Some features of this site may not work without it.

FuCiTNet: improving the generalization of deep learning networks by the fusion of learned class-inherent transformations

Thumbnail
Ver/Abrir
main article (366,2Kb)
Comparte:
 
 
10.1016/j.inffus.2020.06.015
 
  Ver Estadísticas de uso
Cita com:
hdl:2117/328939

Mostrar el registro completo del ítem
Rey-Arena, Manuel
Guirado, Emilio
Tabik, Siham
Ruiz Hidalgo, JavierMés informacióMés informacióMés informació
Tipo de documentoArtículo
Fecha de publicación2020-10
EditorElsevier
Condiciones de accesoAcceso abierto
Attribution-NonCommercial-NoDerivs 3.0 Spain
Salvo que se indique lo contrario, los contenidos de esta obra estan sujetos a la licencia de Creative Commons : Reconocimiento-NoComercial-SinObraDerivada 3.0 España
Resumen
It is widely known that very small datasets produce overfitting in Deep Neural Networks (DNNs), i.e., the network becomes highly biased to the data it has been trained on. This issue is often alleviated using transfer learning, regularization techniques and/or data augmentation. This work presents a new approach, independent but complementary to the previous mentioned techniques, for improving the generalization of DNNs on very small datasets in which the involved classes share many visual features. The proposed model, called FuCiTNet (Fusion Class inherent Transformations Network), inspired by GANs, creates as many generators as classes in the problem. Each generator, k, learns the transformations that bring the input image into the k-class domain. We introduce a classification loss in the generators to drive the leaning of specific k-class transformations. Our experiments demonstrate that the proposed transformations improve the generalization of the classification model in three diverse datasets.
Descripción
© <2020>. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
CitaciónRey-Arena, M. [et al.]. FuCiTNet: improving the generalization of deep learning networks by the fusion of learned class-inherent transformations. "Information fusion", Octubre 2020, vol. 63, p. 188-195. 
URIhttp://hdl.handle.net/2117/328939
DOI10.1016/j.inffus.2020.06.015
ISSN1566-2535
Versión del editorhttps://www.sciencedirect.com/science/article/abs/pii/S1566253520303122
Colecciones
  • Departament de Teoria del Senyal i Comunicacions - Articles de revista [2.351]
  • GPI - Grup de Processament d'Imatge i Vídeo - Articles de revista [117]
Comparte:
 
  Ver Estadísticas de uso

Mostrar el registro completo del ítem

FicherosDescripciónTamañoFormatoVer
2020_FUCINET_PREPRINT.pdfmain article366,2KbPDFVer/Abrir

Listar

Esta colecciónPor fechaAutoresOtras contribucionesTítulosMateriasEste repositorioComunidades & coleccionesPor fechaAutoresOtras contribucionesTítulosMaterias

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • Sobre esta web
  • Contacto
  • Sugerencias
  • Inici de la pàgina