Large-Scale Visual Search with Binary Distributed Graph at Alibaba

TL;DR

This paper introduces a Binary Distributed Graph algorithm for large-scale visual search, enabling rapid offline graph construction and efficient online retrieval on billions of images, outperforming existing methods.

Contribution

It presents a novel binary code-based graph construction method optimized for distributed systems, significantly improving scalability and speed for billion-scale visual search.

Findings

Builds a billion-scale graph in hours

Achieves comparable performance to real-value methods

Outperforms state-of-the-art in large-scale experiments

Abstract

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.