Fast Spectral Ranking for Similarity Search

Abstract : Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the mani-folds online remains expensive even if a nearest neighbor graph has been computed offline. This work introduces an explicit embedding reducing manifold search to Euclidean search followed by dot product similarity search. This is equivalent to linear graph filtering of a sparse signal in the frequency domain. To speed up online search, we compute an approximate Fourier basis of the graph offline. We improve the state of art on particular object retrieval datasets including the challenging Instre dataset containing small objects. At a scale of 10 5 images, the offline cost is only a few hours, while query time is comparable to standard similarity search.
Type de document :
Communication dans un congrès
IEEE Computer Vision and Pattern Recognition Conference, Jun 2018, Salt Lake City, France
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger
Contributeur : Teddy Furon <>
Soumis le : lundi 16 juillet 2018 - 08:46:56
Dernière modification le : mardi 24 juillet 2018 - 01:08:40


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


  • HAL Id : hal-01839744, version 1


Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondřej Chum. Fast Spectral Ranking for Similarity Search. IEEE Computer Vision and Pattern Recognition Conference, Jun 2018, Salt Lake City, France. 〈hal-01839744〉



Consultations de la notice


Téléchargements de fichiers