Early burst detection for memory-efficient image retrieval: – Extended version –

Abstract : Recent works show that image comparison based on local descriptors is corrupted by visual bursts, which tend to dominate the image similarity. The existing strategies, like power-law normalization, improve the results by discounting the contribution of visual bursts to the image similarity. In this paper, we propose to explicitly detect the visual bursts in an image at an early stage. We compare several detection strategies jointly taking into account feature similarity and geometrical quantities. The bursty groups are merged into meta-features, which are used as input to state-of-the-art image search systems such as VLAD or the selective match kernel. Then, we show the interest of using this strategy in an asymmetrical manner, with only the database features being aggregated but not those of the query. Extensive experiments performed on public benchmarks for visual retrieval show the benefits of our method, which achieves performance on par with the state of the art but with a significantly reduced complexity, thanks to the lower number of features fed to the indexing system.
Type de document :
[Research Report] Inria Rennes. 2015
Liste complète des métadonnées

Littérature citée [45 références]  Voir  Masquer  Télécharger

Contributeur : Miaojing Shi <>
Soumis le : lundi 22 juin 2015 - 13:49:46
Dernière modification le : samedi 1 décembre 2018 - 19:56:17
Document(s) archivé(s) le : mardi 15 septembre 2015 - 20:31:29


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01166239, version 1


Miaojing Shi, Yannis Avrithis, Hervé Jégou. Early burst detection for memory-efficient image retrieval: – Extended version –. [Research Report] Inria Rennes. 2015. 〈hal-01166239〉



Consultations de la notice


Téléchargements de fichiers