Content area

Abstract

This paper proposes a decorrelation scheme based on product quantization, termed Reference-Vector Removed Product Quantization (RvRPQ), for approximate nearest neighbor (ANN) search. The core idea is to capture the redundancy among database vectors by representing them with compactly encoded reference-vectors, which are then subtracted from the original vectors to yield residual vectors. We provide a theoretical derivation for obtaining the optimal reference-vectors. This preprocessing step significantly improves the quantization accuracy of the subsequent product quantization applied to the residuals. To maintain low online computational complexity and control memory overhead, we apply vector quantization to the reference-vectors and allocate only a small number of additional bits to store their indices. Experimental results show that RvRPQ substantially outperforms state-of-the-art ANN methods in terms of retrieval accuracy, while preserving high search efficiency.

Details

1009240
Title
Reference-Vector Removed Product Quantization for Approximate Nearest Neighbor Search
Author
Publication title
Volume
15
Issue
21
First page
11540
Number of pages
22
Publication year
2025
Publication date
2025
Publisher
MDPI AG
Place of publication
Basel
Country of publication
Switzerland
Publication subject
e-ISSN
20763417
Source type
Scholarly Journal
Language of publication
English
Document type
Journal Article
Publication history
 
 
Online publication date
2025-10-29
Milestone dates
2025-09-30 (Received); 2025-10-27 (Accepted)
Publication history
 
 
   First posting date
29 Oct 2025
ProQuest document ID
3271550648
Document URL
https://www.proquest.com/scholarly-journals/reference-vector-removed-product-quantization/docview/3271550648/se-2?accountid=208611
Copyright
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Last updated
2025-11-13
Database
ProQuest One Academic