Skip to Main content Skip to Navigation
Journal articles

Explicit embeddings for nearest neighbor search with Mercer kernels

Abstract : Many approximate nearest neighbor search algorithms operate under memory constraints, by computing short signatures for database vectors while roughly keeping the neighborhoods for the distance of interest. Encoding procedures designed for the Euclidean distance have attracted much attention in the last decade.In the case where the distance of interest is based on a Mercer kernel, we propose a simple, yet effective two-step encoding scheme: first, compute an explicit embedding to map the initial space into a Euclidean space; second, apply an encoding step designed to work with the Euclidean distance. Comparing this simple baseline with existing methods relying on implicit encoding, we demonstrate better search recall for similar code sizes with the chi-square kernel in databases comprised of visual descriptors, outperforming concurrent state-of-the-art techniques by a large margin.
Document type :
Journal articles
Complete list of metadata

Cited literature [30 references]  Display  Hide  Download
Contributor : Anthony Bourrier Connect in order to contact the contributor
Submitted on : Tuesday, February 17, 2015 - 5:00:10 PM
Last modification on : Tuesday, October 19, 2021 - 11:58:59 PM
Long-term archiving on: : Monday, May 18, 2015 - 10:45:55 AM


Files produced by the author(s)



Anthony Bourrier, Florent Perronnin, Rémi Gribonval, Patrick Pérez, Hervé Jégou. Explicit embeddings for nearest neighbor search with Mercer kernels. Journal of Mathematical Imaging and Vision, Springer Verlag, 2015, 52 (3), pp.459-468. ⟨10.1007/s10851-015-0555-2⟩. ⟨hal-00722635v4⟩



Record views


Files downloads