Triangulation embedding and democratic aggregation for image search

Hervé Jégou 1 Andrew Zisserman 2
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : We consider the design of a single vector representation for an image that embeds and aggregates a set of local patch descriptors such as SIFT. More specifically we aim to construct a dense representation, like the Fisher Vector or VLAD, though of small or intermediate size. We make two contributions, both aimed at regularizing the individual contributions of the local descriptors in the final representation. The first is a novel embedding method that avoids the dependency on absolute distances by encoding directions. The second contribution is a ''democratization" strategy that further limits the interaction of unrelated descriptors in the aggregation stage. These methods are complementary and give a substantial performance boost over the state of the art in image search with short or mid-size vectors, as demonstrated by our experiments on standard public image retrieval benchmarks.
Document type :
Conference papers
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download


https://hal.inria.fr/hal-00977321
Contributor : Hervé Jégou <>
Submitted on : Monday, April 14, 2014 - 11:37:54 AM
Last modification on : Friday, November 16, 2018 - 1:21:57 AM
Long-term archiving on : Monday, April 10, 2017 - 12:50:13 PM

Files

cvpr2014_democratic_appendices...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00977321, version 2

Citation

Hervé Jégou, Andrew Zisserman. Triangulation embedding and democratic aggregation for image search. CVPR - International Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, United States. ⟨hal-00977321v2⟩

Share

Metrics

Record views

5365

Files downloads

4289