Fast Spectral Ranking for Similarity Search

Ahmet Iscen 1 Yannis Avrithis 2 Giorgos Tolias 1 Teddy Furon 2 Ondrej 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 : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [73 references]  Display  Hide  Download

https://hal.inria.fr/hal-02370336
Contributor : Yannis Avrithis <>
Submitted on : Tuesday, November 19, 2019 - 1:48:01 PM
Last modification on : Thursday, November 21, 2019 - 1:21:05 AM

File

1703.06935.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02370336, version 1
  • ARXIV : 1703.06935

Citation

Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum. Fast Spectral Ranking for Similarity Search. 2017. ⟨hal-02370336⟩

Share

Metrics

Record views

42

Files downloads

36