Show simple item record

dc.contributor.authorJiménez, Albert
dc.contributor.authorAlvarez, Jose M.
dc.contributor.authorGiró Nieto, Xavier
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2017-09-14T08:40:57Z
dc.date.available2017-09-14T08:40:57Z
dc.date.issued2017
dc.identifier.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.
dc.identifier.urihttp://hdl.handle.net/2117/107619
dc.description.abstractImage 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.
dc.format.extent12 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcshImage processing--Digital techniques
dc.subject.lcshSemantic computing
dc.subject.lcshSemantic Web
dc.titleClass-weighted convolutional features for visual instance search
dc.typeConference lecture
dc.subject.lemacImatges -- Processament -- Tècniques digitals
dc.subject.lemacWeb semàntica
dc.subject.lemacSemàntica -- Informàtica
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.relation.publisherversionhttps://bmvc2017.london/programme-1/
dc.rights.accessOpen Access
local.identifier.drac21478027
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/TEC2013-43935-R
local.citation.authorJiménez, A.; Alvarez, J.; Giro, X.
local.citation.contributorBritish Machine Vision Conference
local.citation.pubplaceLondon
local.citation.publicationNameProceedings of the 28th British Machine Vision Conference 2017
local.citation.startingPage1
local.citation.endingPage12


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

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