Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2018

Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking

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.
Fichier principal
Vignette du fichier
paper.pdf (362.76 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01909348 , version 1 (31-10-2018)
hal-01909348 , version 2 (31-10-2018)

Identifiers

  • HAL Id : hal-01909348 , version 2

Cite

Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondřej Chum. Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking. ACCV 2018 - Asian Conference on Computer Vision, Dec 2018, Perth, Australia. pp.1-16. ⟨hal-01909348v2⟩
111 View
152 Download

Share

More