GGNN: Graph-based GPU Nearest Neighbor Search release_appkxbhi5bbpfakfbwpfdxlimi

by Fabian Groh, Lukas Ruppert, Patrick Wieschollek, Hendrik P.A. Lensch

Released as a article .

2019  

Abstract

Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory representations. Since PQT and FAISS started to leverage the massive parallelism offered by GPUs, GPU-based implementations are a crucial resource for today's state-of-the-art ANN methods. While most of these methods allow for faster queries, less emphasis is devoted to accelerate the construction of the underlying index structures. In this paper, we propose a novel search structure based on nearest neighbor graphs and information propagation on graphs. Our method is designed to take advantage of GPU architectures to accelerate the hierarchical building of the index structure and for performing the query. Empirical evaluation shows that GGNN significantly surpasses the state-of-the-art GPU- and CPU-based systems in terms of build-time, accuracy and search speed.
In text/plain format

Archived Files and Locations

application/pdf  387.3 kB
file_uvtzn47be5denlan2724xofyai
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-12-04
Version   v2
Language   en ?
arXiv  1912.01059v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 1f76d10a-b97b-4c41-a211-423b614ff0d4
API URL: JSON