Early burst detection for memory-efficient image retrieval

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 :
Communication dans un congrès
Computer Vision and Pattern Recognition, Jun 2015, Boston, United States
Liste complète des métadonnées

https://hal.inria.fr/hal-01146533
Contributeur : Hervé Jégou <>
Soumis le : mardi 28 avril 2015 - 14:51:55
Dernière modification le : mercredi 2 août 2017 - 10:08:34
Document(s) archivé(s) le : mercredi 19 avril 2017 - 09:03:22

Fichiers

burst.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01146533, version 1

Citation

Miaojing Shi, Yannis Avrithis, Hervé Jégou. Early burst detection for memory-efficient image retrieval. Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. <hal-01146533>

Partager

Métriques

Consultations de
la notice

352

Téléchargements du document

352