Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
61.586 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Departaments
  • Departament de Teoria del Senyal i Comunicacions
  • Articles de revista
  • View Item
  •   DSpace Home
  • E-prints
  • Departaments
  • Departament de Teoria del Senyal i Comunicacions
  • Articles de revista
  • View Item
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
View/Open
main article (366,2Kb)
 
10.1016/j.inffus.2020.06.015
 
  View Usage Statistics
  LA Referencia / Recolecta stats
Cita com:
hdl:2117/328939

Show full item record
Rey-Arena, Manuel
Guirado, Emilio
Tabik, Siham
Ruiz Hidalgo, JavierMés informacióMés informacióMés informació
Document typeArticle
Defense date2020-10
PublisherElsevier
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
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.
Description
© <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/
CitationRey-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
Publisher versionhttps://www.sciencedirect.com/science/article/abs/pii/S1566253520303122
Collections
  • Departament de Teoria del Senyal i Comunicacions - Articles de revista [2.449]
  • GPI - Grup de Processament d'Imatge i Vídeo - Articles de revista [118]
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
2020_FUCINET_PREPRINT.pdfmain article366,2KbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

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

info.biblioteques@upc.edu

  • About This Repository
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina