Dynamicity and Durability in Scalable Visual Instance Search

TL;DR

This paper extends the NV-tree index to support dynamic and durable scalable visual instance search, enabling efficient insertions and recoverability in billion-scale image collections.

Contribution

It introduces a transactional NV-tree that enforces ACID properties, ensuring dynamicity and durability in large-scale high-dimensional indexing.

Findings

High insertion throughput maintained with ACID overhead

Scalable indexing demonstrated on collections up to 28.5 billion vectors

Largest single-server evaluations reported in the literature

Abstract

Visual instance search involves retrieving from a collection of images the ones that contain an instance of a visual query. Systems designed for visual instance search face the major challenge of scalability: a collection of a few million images used for instance search typically creates a few billion features that must be indexed. Furthermore, as real image collections grow rapidly, systems must also provide dynamicity, i.e., be able to handle on-line insertions while concurrently serving retrieval operations. Durability, which is the ability to recover correctly from software and hardware crashes, is the natural complement of dynamicity. Durability, however, has rarely been integrated within scalable and dynamic high-dimensional indexing solutions. This article addresses the issue of dynamicity and durability for scalable indexing of very large and rapidly growing collections of local features for instance retrieval. By extending the NV-tree, a scalable disk-based high-dimensional index, we show how to implement the ACID properties of transactions which ensure both dynamicity and durability. We present a detailed performance evaluation of the transactional NV-tree: (i) We show that the insertion throughput is excellent despite the overhead for enforcing the ACID properties; (ii) We also show that this transactional index is truly scalable using a standard image benchmark embedded in collections of up to 28.5 billion high-dimensional vectors; the largest single-server evaluations reported in the literature.