阿里巴巴基于二进制分布图的大规模可视化搜索
Large-Scale Visual Search with Binary Distributed Graph at Alibaba
摘要：
基于图的近似最近邻搜索因其在线搜索的优势而受到越来越多的关注。人们提出了许多提高检索速度和查全率的方法。然而，很少有人关注离线图构建的效率和规模。对于一个拥有数十亿在线图像的视觉搜索系统来说，在数小时内构建一个数十亿规模的离线图是至关重要的，这几乎是现有方法无法实现的。在本文中，我们提出了一种新的算法称为二进制分布图来解决这个问题。具体来说，我们结合二进制代码与图形结构，以加速在线和离线过程，并通过召回更多的二进制候选人，实现与基于实值的场景中的性能相当。此外，图的构造被优化为完全分布式的实现，这大大加快了离线过程，摆脱了内存和磁盘的限制在一台机器。在阿里巴巴商品数据集（超过30亿张图片）上的实验比较表明，该方法在在线/离线权衡方面优于现有技术。
英文摘要：
Graph-based approximate nearest neighbor search has attracted more and more attentions due to its online search advantages. Numbers of methods studying the enhancement of speed and recall have been put forward. However, few of them focus on the efficiency and scale of offline graph-construction. For a deployed visual search system with several billions of online images in total, building a billion-scale offline graph in hours is essential, which is almost unachievable by most existing methods. In this paper, we propose a novel algorithm called Binary Distributed Graph to solve this problem. Specifically, we combine binary codes with graph structure to speedup online and offline procedures, and achieve comparable performance with the ones in real-value based scenarios by recalling more binary candidates. Furthermore, the graph-construction is optimized to completely distributed implementation, which significantly accelerates the offline process and gets rid of the limitation of memory and disk within a single machine. Experimental comparisons on Alibaba Commodity Data Set (more than three billion images) show that the proposed method outperforms the state-of-the-art with respect to the online/offline trade-off.
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。
