Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

Ahmet Iscen 1 Yannis Avrithis 2 Giorgos Tolias 1 Teddy Furon 2 Ondřej Chum 1
1 VRG - Visual Recognition Group [Prague]
CTU/FEE - Faculty of electrical engineering [Prague]
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA_D6 - MEDIA ET INTERACTIONS
Abstract : State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founded hybrid filtering approach allowing full control of the space-time trade-off between these two extremes. Experimentally , we verify that our hybrid method delivers results on par with the state of the art, with lower memory demands compared to spectral filtering approaches and faster compared to temporal filtering.
Type de document :
Rapport
[Research Report] Inria Rennes - Bretagne Atlantique. 2018, pp.1-16
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01846002
Contributeur : Yannis Avrithis <>
Soumis le : vendredi 20 juillet 2018 - 16:57:19
Dernière modification le : jeudi 15 novembre 2018 - 11:59:01
Document(s) archivé(s) le : dimanche 21 octobre 2018 - 20:17:40

Fichier

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

Identifiants

  • HAL Id : hal-01846002, version 1

Citation

Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondřej Chum. Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking. [Research Report] Inria Rennes - Bretagne Atlantique. 2018, pp.1-16. 〈hal-01846002〉

Partager

Métriques

Consultations de la notice

123

Téléchargements de fichiers

36