arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1609.05345cs.MMcs.IR
收藏

大规模数据的广义残差向量quantization

Generalized residual vector quantization for large scale data

Shicong Liu, Junru Shao, Hongtao Lu

摘要:

矢量量化是处理大规模数据的重要工具,例如,大规模相似性搜索,这对于基于内容的信息检索和分析至关重要。在本文中,我们提出了一种新的矢量量化框架,迭代最小化量化误差。首先,我们提供了一个相关的矢量量化方法命名为\textit{residual vector quantization}(RVQ)的详细审查。接下来,我们提出了\textit{generalized residual vector quantization}(GRVQ),以进一步改善RVQ。许多矢量量化方法可以被视为我们提出的框架的特殊情况。我们在几个大规模的基准数据集上评估GRVQ,用于大规模搜索,分类和对象检索。我们比较了GRVQ与现有的方法。大量的实验表明,我们的GRVQ框架大大优于现有的方法在量化精度和计算效率。

英文摘要:

Vector quantization is an essential tool for tasks involving large scale data, for example, large scale similarity search, which is crucial for content-based information retrieval and analysis. In this paper, we propose a novel vector quantization framework that iteratively minimizes quantization error. First, we provide a detailed review on a relevant vector quantization method named \textit{residual vector quantization} (RVQ). Next, we propose \textit{generalized residual vector quantization} (GRVQ) to further improve over RVQ. Many vector quantization methods can be viewed as the special cases of our proposed framework. We evaluate GRVQ on several large scale benchmark datasets for large scale search, classification and object retrieval. We compared GRVQ with existing methods in detail. Extensive experiments demonstrate our GRVQ framework substantially outperforms existing methods in term of quantization accuracy and computation efficiency.

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。

↑