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
59.781 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Grups de recerca
  • GPI - Grup de Processament d'Imatge i Vídeo
  • Ponències/Comunicacions de congressos
  • View Item
  •   DSpace Home
  • E-prints
  • Grups de recerca
  • GPI - Grup de Processament d'Imatge i Vídeo
  • Ponències/Comunicacions de congressos
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Class-weighted convolutional features for visual instance search

Thumbnail
View/Open
Main paper (3,489Mb)
Poster (3,659Mb)
Share:
 
  View Usage Statistics
Cita com:
hdl:2117/107619

Show full item record
Jiménez, Albert
Alvarez, Jose M.
Giró Nieto, XavierMés informacióMés informació
Document typeConference lecture
Defense date2017
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
ProjectPROCESADO DE INFORMACION HETEROGENEA Y SEÑALES EN GRAFOS PARA BIG DATA. APLICACION EN CRIBADO DE ALTO RENDIMIENTO, TELEDETECCION, MULTIMEDIA Y HCI. (MINECO-TEC2013-43935-R)
Abstract
Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional neural networks trained for image classification over large datasets have been proven effective feature extractors for image retrieval. The most successful approaches are based on encoding the activations of convolutional layers, as they convey the image spatial information. In this paper, we go beyond this spatial information and propose a local-aware encoding of convolutional features based on semantic information predicted in the target image. To this end, we obtain the most discriminative regions of an image using Class Activation Maps (CAMs). CAMs are based on the knowledge contained in the network and therefore, our approach, has the additional advantage of not requiring external information. In addition, we use CAMs to generate object proposals during an unsupervised re-ranking stage after a first fast search. Our experiments on two public available datasets for instance retrieval, Oxford5k and Paris6k, demonstrate the competitiveness of our approach outperforming the current state-of-the-art when using off-the-shelf models trained on ImageNet.
CitationJiménez, A., Alvarez, J., Giro, X. Class-weighted convolutional features for visual instance search. A: British Machine Vision Conference. "Proceedings of the 28th British Machine Vision Conference 2017". London: 2017, p. 1-12. 
URIhttp://hdl.handle.net/2117/107619
Publisher versionhttps://bmvc2017.london/programme-1/
Collections
  • GPI - Grup de Processament d'Imatge i Vídeo - Ponències/Comunicacions de congressos [317]
  • Departament de Teoria del Senyal i Comunicacions - Ponències/Comunicacions de congressos [3.230]
Share:
 
  View Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
jimenez-bmvc-2017-paper.pdfMain paper3,489MbPDFView/Open
jimenez-bmvc-2017-poster.pdfPoster3,659MbPDFView/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