Revisiting The Inverted Indices For Billion-scale Approximate Nearest Neighbors

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 effici

Stats

• citations64
• S2 citations—
• github stars0
• HF likes0
• heat score13.60
• arxiv keybaranchuk2018revisiting

Related papers

• Billion-scale Similarity Search Using A Hybrid Indexing Approach With Advanced Filtering (2025)4.52
• Efficient Inverted Indexes For Approximate Retrieval Over Learned Sparse Representations (2024)11.67
• Hybrid Inverted Index Is A Robust Accelerator For Dense Retrieval (2022)7.07
• Hd-index: Pushing The Scalability-accuracy Boundary For Approximate Knn Search In High-dimensional Spaces (2018)14.02
• Results Of The Neurips'21 Challenge On Billion-scale Approximate Nearest Neighbor Search (2022)0.00
• Large Scale Deep Convolutional Neural Network Features Search With Lucene (2016)0.00
• Compact Hash Codes For Efficient Visual Descriptors Retrieval In Large Scale Databases (2016)11.76
• SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search (2021)0.00