Approximate nearest neighbor search by cyclic hierarchical product quantization

Guardado en:
Detalles Bibliográficos
Publicado en:Signal, Image and Video Processing vol. 19, no. 6 (Jun 2025), p. 452
Autor principal: Xu, Zhi
Otros Autores: Zhou, Mengdong, Liu, Yuxuan, Zhao, Longyang, Liu, Jiajia
Publicado:
Springer Nature B.V.
Materias:
Acceso en línea:Citation/Abstract
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3256842441
003 UK-CbPIL
022 |a 1863-1703 
022 |a 1863-1711 
024 7 |a 10.1007/s11760-025-04030-w  |2 doi 
035 |a 3256842441 
045 2 |b d20250601  |b d20250630 
100 1 |a Xu, Zhi  |u Guilin University of Electronic Technology, School of Computer Science and Information Security, Guilin, China (GRID:grid.440723.6) (ISNI:0000 0001 0807 124X) 
245 1 |a Approximate nearest neighbor search by cyclic hierarchical product quantization 
260 |b Springer Nature B.V.  |c Jun 2025 
513 |a Journal Article 
520 3 |a Vector quantization (VQ) is a widely used Approximate Nearest Neighbor (ANN) search method. By constructing multiple codebooks, VQ can create more codeword vectors with lower memory consumption, enabling the indexing of large-scale database. In recent years, many VQ-based methods have been proposed, but the codeword vectors constructed in these methods are often underutilized due to insufficient data support, and the unimodal data distribution within the partition is not considered. To address these issues, we propose a new quantization method, Cyclic Hierarchical Product Quantization (CHPQ). This method first constructs a hierarchical quantization structure in each subspace, with each hierarchical structure composed of several sub-quantizers. Then, the codebook is locally optimized under the sub-quantizers according to the data distribution of each Voronoi cell, significantly improving quantization performance compared to other methods and greatly enhancing the accuracy of ANN search. Additionally, this paper proposes a new hierarchical quantization structure, termed cyclic hierarchical structure, which can generate more diverse codeword vectors in different space partitions compared to the traditional hierarchical quantization structure. Experiment results demonstrate that CHPQ outperforms existing methods in terms of retrieval accuracy while maintaining comparable computational efficiency. 
653 |a Accuracy 
653 |a Codes 
653 |a Datasets 
653 |a Vector space 
653 |a Search methods 
653 |a Data compression 
653 |a Counters 
653 |a Retrieval performance measures 
700 1 |a Zhou, Mengdong  |u Guilin University of Electronic Technology, School of Computer Science and Information Security, Guilin, China (GRID:grid.440723.6) (ISNI:0000 0001 0807 124X) 
700 1 |a Liu, Yuxuan  |u Guilin University of Electronic Technology, School of Mechanical and Electrical Engineering, Guilin, China (GRID:grid.440723.6) (ISNI:0000 0001 0807 124X) 
700 1 |a Zhao, Longyang  |u Guilin University of Electronic Technology, School of Computer Science and Information Security, Guilin, China (GRID:grid.440723.6) (ISNI:0000 0001 0807 124X) 
700 1 |a Liu, Jiajia  |u Civil Aviation Flight University of China, School of Institute of Electronic and Electrical Engineering, Guanghan, China (GRID:grid.464258.9) (ISNI:0000 0004 1757 4975) 
773 0 |t Signal, Image and Video Processing  |g vol. 19, no. 6 (Jun 2025), p. 452 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3256842441/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch