Query adaptative locality sensitive hashing

Hervé Jégou, Laurent Amsaleg, Cordelia Schmid, Patrick GrosICASSP 2008 · OpenReview

Abstract

It is well known that high-dimensional nearest-neighbor retrieval is very expensive. Many signal processing methods suffer from this computing cost. Dramatic performance gains can be obtained by using approximate search, such as the popular Locality-Sensitive Hashing. This paper improves LSH by performing an on-line selection of the most appropriate hash functions from a pool of functions. An additional improvement originates from the use of E& lattices for geometric hashing instead of one-dimensional random projections. A performance study based on state-of-the-art high-dimensional descriptors computed on real images shows that our improvements to LSH greatly reduce the search complexity for a given level of accuracy.
BibTeX
@inproceedings{jegou2008query,
  author = {Hervé Jégou and Laurent Amsaleg and Cordelia Schmid and Patrick Gros},
  title = {{Query adaptative locality sensitive hashing}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2008},
  url = {https://openreview.net/forum?id=ka4-WeBVrp},
}

Loading related content...

Figure