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
60.707 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Centres de recerca
  • BSC - Barcelona Supercomputing Center
  • Computer Sciences
  • Articles de revista
  • View Item
  •   DSpace Home
  • E-prints
  • Centres de recerca
  • BSC - Barcelona Supercomputing Center
  • Computer Sciences
  • Articles de revista
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

A visual embedding for the unsupervised extraction of abstract semantics

Thumbnail
View/Open
visual_CogSys.pdf (4,207Mb)
Share:
 
 
10.1016/j.cogsys.2016.11.008
 
  View Usage Statistics
Cita com:
hdl:2117/100191

Show full item record
García Gasulla, Dario
Ayguadé Parra, EduardMés informacióMés informacióMés informació
Labarta Mancho, Jesús JoséMés informacióMés informacióMés informació
Béjar Alonso, JavierMés informacióMés informacióMés informació
Cortés García, Claudio UlisesMés informacióMés informacióMés informació
Suzumura, Toyotaro
Chen, R
Document typeArticle
Defense date2017-05-01
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 4.0 International
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 4.0 International
ProjectCOMPUTACION DE ALTAS PRESTACIONES VII (MINECO-TIN2015-65316-P)
Abstract
Vector-space word representations obtained from neural network models have been shown to enable semantic operations based on vector arithmetic. In this paper, we explore the existence of similar information on vector representations of images. For that purpose we define a methodology to obtain large, sparse vector representations of image classes, and generate vectors through the state-of-the-art deep learning architecture GoogLeNet for 20 K images obtained from ImageNet. We first evaluate the resultant vector-space semantics through its correlation with WordNet distances, and find vector distances to be strongly correlated with linguistic semantics. We then explore the location of images within the vector space, finding elements close in WordNet to be clustered together, regardless of significant visual variances (e.g., 118 dog types). More surprisingly, we find that the space unsupervisedly separates complex classes without prior knowledge (e.g., living things). Afterwards, we consider vector arithmetics. Although we are unable to obtain meaningful results on this regard, we discuss the various problem we encountered, and how we consider to solve them. Finally, we discuss the impact of our research for cognitive systems, focusing on the role of the architecture being used.
CitationGarcía-Gasulla, D., Ayguadé, E., Labarta, J., Béjar, J., Cortés, U., Suzumura, T., Chen, R. A visual embedding for the unsupervised extraction of abstract semantics. "Cognitive systems research", 1 Maig 2017, vol. 42, p. 73-81. 
URIhttp://hdl.handle.net/2117/100191
DOI10.1016/j.cogsys.2016.11.008
ISSN1389-0417
Publisher versionhttp://www.sciencedirect.com/science/article/pii/S1389041716300444
Collections
  • Computer Sciences - Articles de revista [286]
  • Departament d'Arquitectura de Computadors - Articles de revista [990]
  • Departament de Ciències de la Computació - Articles de revista [974]
  • KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic - Articles de revista [124]
  • CAP - Grup de Computació d'Altes Prestacions - Articles de revista [380]
Share:
 
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
visual_CogSys.pdf4,207MbPDFView/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