Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking - Archive ouverte HAL Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2018

Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

Résumé

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.
Fichier principal
Vignette du fichier
paper.pdf (340.03 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01846002 , version 1 (20-07-2018)

Identifiants

  • HAL Id : hal-01846002 , version 1

Citer

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⟩
146 Consultations
107 Téléchargements

Partager

Gmail Facebook X LinkedIn More