Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

Ahmet Iscen 1 Giorgos Tolias 2 Yannis Avrithis 1 Teddy Furon 1 Ondrej Chum 2
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
2 VRG - Visual Recognition Group [Prague]
CTU/FEE - Faculty of electrical engineering [Prague]
Abstract : Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches. An efficient off-line stage allows optional reduction in the number of stored regions. In the on-line stage, the proposed handling of unseen queries in the indexing stage removes additional computation to adjust the precomputed data. We perform diffusion through a sparse linear system solver, yielding practical query times well below one second. Experimentally, we observe a significant boost in performance of image retrieval with compact CNN descriptors on standard benchmarks, especially when the query object covers only a small part of the image. Small objects have been a common failure case of CNN-based retrieval.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [64 references]  Display  Hide  Download

https://hal.inria.fr/hal-02370330
Contributor : Yannis Avrithis <>
Submitted on : Tuesday, November 19, 2019 - 1:46:06 PM
Last modification on : Thursday, November 21, 2019 - 1:21:05 AM

File

1611.05113.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02370330, version 1
  • ARXIV : 1611.05113

Citation

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum. Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations. 2016. ⟨hal-02370330⟩

Share

Metrics

Record views

30

Files downloads

33