Parametric and nonparametric residual vector quantization optimizations for ANN search

• Published in: Neurocomputing (Amsterdam) Vol. 217; pp. 92 - 102
• Main Authors: Guo, Dan, Li, Chuanqing, Wu, Lv
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 12.12.2016
• Subjects: Nonparametric optimization; Parametric optimization; Residual vector quantization; Stage codebook; Vector quantization optimization; Residual vector quantization; Parametric optimization; Vector quantization optimization; Stage codebook; Nonparametric optimization

For approximate nearest neighbor (ANN) search in many vision-based applications, vector quantization (VQ) is an efficient compact encoding technology. A representative approach of VQ is product quantization (PQ) which quantizes subspaces separately by Cartesian product and achieves high accuracy. Bu...