Fast Nearest Neighbor Search with Narrow 16-bit Sketch

Naoya Higuchi, Yasunobu Imamura, Tetsuji Kuboyama, Kouichi Hirata, Takeshi Shinohara

2019

Abstract

We discuss the nearest neighbor search using sketch which is a kind of locality sensitive hash (LSH). Nearest neighbor search using sketch is done in two stages. In the first stage, the top K candidates, which have close sketches to a query, are selected, where K ≥ 1. In the second stage, the nearest object to the query from K candidates is selected by performing actual distance calculations. Conventionally, higher accurate search requires wider sketches than 32-bit. In this paper, we propose search methods using narrow 16-bit sketch, which enables efficient data management by buckets and implement a faster first stage. To keep accuracy, search using 16-bit sketch requires larger K than using 32-bit sketch. By sorting the data objects according to sketch’s values, cost influence due to the increase in the number of candidates K can be reduced by improving memory locality in the second stage search. The proposed method achieves about 10 times faster search speed while maintaining accuracy.

Paper Citation

in Harvard Style

Higuchi N., Imamura Y., Kuboyama T., Hirata K. and Shinohara T. (2019). Fast Nearest Neighbor Search with Narrow 16-bit Sketch.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 540-547. DOI: 10.5220/0007377705400547

in Bibtex Style

@conference{icpram19,
author={Naoya Higuchi and Yasunobu Imamura and Tetsuji Kuboyama and Kouichi Hirata and Takeshi Shinohara},
title={Fast Nearest Neighbor Search with Narrow 16-bit Sketch},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={540-547},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007377705400547},
isbn={978-989-758-351-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Fast Nearest Neighbor Search with Narrow 16-bit Sketch
SN - 978-989-758-351-3
AU - Higuchi N.
AU - Imamura Y.
AU - Kuboyama T.
AU - Hirata K.
AU - Shinohara T.
PY - 2019
SP - 540
EP - 547
DO - 10.5220/0007377705400547