In this paper, we propose a product quantization table (PQTable); a fast search method for product-quantized codes via hash-tables. An identifier of each database vector is associated with the slot of a hash table by using its PQ-code as a key. For querying, an input vector is PQ-encoded and hashed, and the items associated with that code are then retrieved. The proposed PQTable produces the same results as a linear PQ scan, and is 10^2 to 10^5 times faster. Although state-of-the-art performance can be achieved by previous inverted-indexing-based approaches, such methods require manually-designed parameter setting and significant training; our PQTable is free of these limitations, and therefore offers a practical and effective solution for real-world problems. Specifically, when the vectors are highly compressed, our PQTable achieves one of the fastest search performances on a single CPU to date with significantly efficient memory usage (0.059 ms per query over 10^9 data points with just 5.5 GB memory consumption). Finally, we show that our proposed PQTable can naturally handle the codes of an optimized product quantization (OPQTable).

• Paper
• IEEE Xplore
• Code (Github)

• PQTable: Nonexhaustive Fast Search for Product-Quantized Codes Using Hash Tables
  Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  IEEE Transactions on Multimedia (TMM), 2018 (extended version of ICCV paper)
• PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization using Hash Tables
  Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
  IEEE International Conference on Computer Vision (ICCV), 2015

@article{tmm_matsui_2018,
    author={Yusuke Matsui and Toshihiko Yamasaki and Kiyoharu Aizawa},
    title={PQTable: Nonexhaustive Fast Search for Product-Quantized Codes Using Hash Tables},
    journal={IEEE Transactions on Multimedia},
    volume={20},
    number={7},
    pages={1809-1822},
    year={2018}
}

@inproceedings{iccv_matsui_2015,
    author={Yusuke Matsui and Toshihiko Yamasaki and Kiyoharu Aizawa},
    title={PQTable: Fast Exact Asymmetric Distance Neighbor Search for Product Quantization Using Hash Tables},
    booktitle={IEEE International Conference on Computer Vision (ICCV)},
    pages={1940-1948},
    year={2015}
}