Corpus ID: 155100024

Derived Codebooks for High-Accuracy Nearest Neighbor Search

@article{Andr2019DerivedCF,
  title={Derived Codebooks for High-Accuracy Nearest Neighbor Search},
  author={Fabien Andr{\'e} and Anne-Marie Kermarrec and Nicolas Le Scouarnec},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.06900}
}
  • Fabien André, Anne-Marie Kermarrec, Nicolas Le Scouarnec
  • Published 2019
  • Computer Science
  • ArXiv
  • High-dimensional Nearest Neighbor (NN) search is central in multimedia search systems. Product Quantization (PQ) is a widespread NN search technique which has a high performance and good scalability. PQ compresses high-dimensional vectors into compact codes thanks to a combination of quantizers. Large databases can, therefore, be stored entirely in RAM, enabling fast responses to NN queries. In almost all cases, PQ uses 8-bit quantizers as they offer low response times. In this paper, we… CONTINUE READING

    Citations

    Publications citing this paper.

    Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD

    VIEW 2 EXCERPTS
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 16 REFERENCES

    Optimized Product Quantization

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD

    VIEW 1 EXCERPT

    Product Quantization for Nearest Neighbor Search

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Tree quantization for large-scale similarity search and classification

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Cartesian K-Means

    Additive Quantization for Extreme Vector Compression

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL