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.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-01909348
Contributor : Teddy Furon <>
Submitted on : Wednesday, October 31, 2018 - 9:36:08 AM
Last modification on : Friday, September 13, 2019 - 9:48:07 AM
Long-term archiving on : Friday, February 1, 2019 - 12:48:07 PM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01909348, version 1

Citation

Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondřej Chum. Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking. Asian Conference on Computer Vision, Dec 2018, Perth, Australia. ⟨hal-01909348v1⟩

Share

Metrics

Record views

23

Files downloads

1