arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.05911cs.CV
收藏

基于GPU的高效大规模近似最近邻搜索

Efficient Large-scale Approximate Nearest Neighbor Search on the GPU

Adobe Systems Inc.(Adobe系统公司);Disney Research(迪士尼研究院)

Patrick Wieschollek, Oliver Wang, Alexander Sorkine-Hornung, Hendrik P. A. Lensch

摘要:

我们提出了一种新的方法,有效的近似最近邻(ANN)搜索在高维空间中,扩展了产品量化的想法。我们提出了一个两级产品和矢量量化树,减少了在树遍历所需的矢量比较的数量。我们的方法还包括一个新的高度并行化的重新排序候选向量的方法,有效地重用已经计算的中间值。由于其遍历过程中的内存占用量小,该方法适合于高效的并行GPU实现。这种乘积量化树(PQT)方法在标准参考数据集上的高维最近邻查询中明显优于最新的最先进的方法。我们的工作是第一个证明GPU性能优于CPU性能的高维,大规模人工神经网络问题在时间关键的现实世界的应用,如闭环视频。

英文摘要:

We present a new approach for efficient approximate nearest neighbor (ANN) search in high dimensional spaces, extending the idea of Product Quantization. We propose a two-level product and vector quantization tree that reduces the number of vector comparisons required during tree traversal. Our approach also includes a novel highly parallelizable re-ranking method for candidate vectors by efficiently reusing already computed intermediate values. Due to its small memory footprint during traversal, the method lends itself to an efficient, parallel GPU implementation. This Product Quantization Tree (PQT) approach significantly outperforms recent state of the art methods for high dimensional nearest neighbor queries on standard reference datasets. Ours is the first work that demonstrates GPU performance superior to CPU performance on high dimensional, large scale ANN problems in time-critical real-world applications, like loop-closing in videos.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑