Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors

TL;DR

This paper demonstrates that a well-optimized inverted index can outperform the more complex multi-index approach for billion-scale approximate nearest neighbor search, especially with deep descriptors.

Contribution

The authors introduce a retrieval system based on the inverted index that surpasses the multi-index in speed and accuracy for billion-scale datasets.

Findings

Inverted index outperforms multi-index in recall and speed.

System achieves state-of-the-art results on billion-scale deep descriptors.

Comparable memory and complexity with significantly improved performance.

Abstract

This work addresses the problem of billion-scale nearest neighbor search. The state-of-the-art retrieval systems for billion-scale databases are currently based on the inverted multi-index, the recently proposed generalization of the inverted index structure. The multi-index provides a very fine-grained partition of the feature space that allows extracting concise and accurate short-lists of candidates for the search queries. In this paper, we argue that the potential of the simple inverted index was not fully exploited in previous works and advocate its usage both for the highly-entangled deep descriptors and relatively disentangled SIFT descriptors. We introduce a new retrieval system that is based on the inverted index and outperforms the multi-index by a large margin for the same memory consumption and construction complexity. For example, our system achieves the state-of-the-art recall rates several times faster on the dataset of one billion deep descriptors compared to the efficient implementation of the inverted multi-index from the FAISS library.