Skip to main content
SpringerLink
Log in

Optimized residual vector quantization for efficient approximate nearest neighbor search

  • Regular Paper
  • Published:
Multimedia Systems Aims and scope Submit manuscript

Abstract

In this paper, an optimized residual vector quantization-based approach is presented for improving the quality of vector quantization and approximate nearest neighbor search. The main contributions are as follows. Based on residual vector quantization (RVQ), a joint optimization process called enhanced RVQ (ERVQ) is introduced. Each stage codebook is iteratively optimized by the others aiming at minimizing the overall quantization errors. Thus, an input vector is approximated by its quantization outputs more accurately. Consequently, the precision of approximate nearest neighbor search is improved. To efficiently find nearest centroids when quantizing vectors, a non-linear vector quantization method is proposed. The vectors are embedded into 2-dimensional space where the lower bounds of Euclidean distances between the vectors and centroids are calculated. The lower bound is used to filter non-nearest centroids for the purpose of reducing computational costs. ERVQ is noticeably optimized in terms of time efficiency on quantizing vectors when combining with this method. To evaluate the accuracy that vectors are approximated by their quantization outputs, an ERVQ-based exhaustive method for approximate nearest neighbor search is implemented. Experimental results on three datasets demonstrate that our approaches outperform the state-of-the-art methods over vector quantization and approximate nearest neighbor search.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in video. In: ICCV, pp. 1470–1477 (2003)

  2. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–100 (2004)

    Article  Google Scholar 

  3. Bohm, C., Berchtold, S., Keim, D.A.: Searching in high-dimensional spaces: index structures for improving the performance of multimedia databases. ACM Comput. Surv. 33(3), 322–373 (2001)

    Article  Google Scholar 

  4. Jegou, H., Matthijs, D., Cordelia, S.: Product quantization for nearest neighbor search. IEEE Trans. PAMI 33(1), 117–128 (2011)

    Article  Google Scholar 

  5. Bentley, J.L.: Multidimensional binary search trees used for associative searching. Commun. ACM 18(9), 509–517 (1975)

    Article  MATH  Google Scholar 

  6. Silpa-Anan C., Hartley R.: Optimised kd-trees for fast image descriptor matching. In: CVPR, pp. 1–8 (2008)

  7. Jia Y., Wang J., Zeng G., Zha H., Hua X. S.: Optimizing kd-trees for scalable visual descriptor indexing. In: CVPR, pp. 3392–3399 (2010)

  8. Wang, J., Wang, N., Jia, Y., Li, J., Zeng, G., Zha, H., Hua, X.S.: Triary-projection trees for approximate nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 36(2), 388–403 (2014)

    Article  Google Scholar 

  9. Philbin J., Chum O., Isard M., Sivic J., Zisserman A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR, pp. 1–8 (2007)

  10. Nister D., Stewenius H.: Scalable recognition with a vocabulary tree. In: CVPR, pp. 2161–2168 (2006)

  11. Muja M., Lowe D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. In: VISSSAPP, pp. 331–340 (2009)

  12. Data, M., Immorlica, N., Indyk, P., Mirrokni, D.V.S.: Locality-sensitive hashing scheme based on p-stable distributions. In: Symposium on Computational geometry, pp. 253–262 (2004)

  13. Panigrahy, R.: Entropy based nearest neighbor search in high dimensions. In: ACM-SIAM SODA, pp. 1186–1195 (2006)

  14. Lv, Q., Josephson, W., Wang, Z., Charikar, M., Li, K.: Multi-Probe LSH: Efficient indexing for high-dimensional similarity search. In: VLDB, pp. 950–961 (2007)

  15. Kuo, Y. H., Chen, K.T.C., Chiang, H., Hsu, W.H.: Query expansion for hash-based image object retrieval. In: ACM Conference on Multimedia, pp. 65–74 (2009)

  16. Jegou, H., Amsaleg, L., Schmid, C., Gros, P.: Query-adaptative locality sensitive hashing. In: Conference on ICASSP, pp. 825–828 (2008)

  17. Torralba, A., Fergus, R., Weiss, Y.: Small codes and large image databases for recognition. In: International conference on CVPR, pp. 1–8 (2008)

  18. Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS, pp. 1753–1760 (2009)

  19. Heo, J.P., Lee, Y., He, J., Chang, S.F., Yoon, S.E.: Spherical hashing. In: International conference on CVPR, pp. 2957–2964 (2012)

  20. Jegou, H., Douze, M., Schmid, C.: Improving Bag-of-Features for Large Scale Image Search. Int J Comput Vision 87(3), 316–336 (2010)

    Article  Google Scholar 

  21. Jegou, H., Douze, M., Schmid, C.: Packing bag-of-features. In: International Conference on Computer Vision (ICCV), pp. 2357–2364 (2009)

  22. He, K., Wen, F., Sun, J.: K-means Hashing: an affinity-preserving quantization method for learning Binary Compact Codes. In: International Conference on CVPR, pp. 2938–2945 (2013)

  23. Hajebi, K., Yadkori, Y.A., Shahbazi H., Zhang H.: Fast approximate nearest-neighbor search with k-nearest neighbor graph. In: IJCAI, pp. 1312–1317 (2011)

  24. Wang, J., Wang, J., Zeng, G., Tu, Z., Gan, R., Li, S.: Scalable k-nn graph construction for visual search. In: CVPR, pp. 1106–1113 (2012)

  25. Wang, J., Li, S.: Query-Driven Iterated Neighborhood Graph Search for Large Scale Indexing. In: ACM Multimedia, pp. 179–188 (2012)

  26. Wang, J., Wang, J., Zeng, G., Gan, R., Li, S., Guo, B.: Fast Neighborhood Graph Search using Cartesian Concatenation., In: ICCV, pp. 2128–2135 (2013)

  27. Brandt, J.: Transform coding for fast approximate nearest neighbor search in high dimensions. In: International conference on CVPR, pp. 1815–1822 (2010)

  28. Chen, Y., Guan, T., Wang, C.: Approximate nearest neighbor search by residual vector quantization. Sensors 10, 11259–11273 (2010)

    Article  Google Scholar 

  29. Babenko, A., Lempitsky, V.: The Inverted multi-index. In: International Conference on CVPR, pp. 3069–3076 (2012)

  30. Jegou, H., Tavenard, R., Douze, M., Amsaleg, L.: Search in one Billion Vectors: re-rank with Source Coding. In: IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), pp. 861–864 (2011)

  31. Ge, T., He, K., Ke, Q., Sun, J.: Optimized product quantization for approximate nearest neighbor search. In: International Conference on CVPR, pp. 2946–2953 (2013)

  32. Gray, R., Neuhoff, D.: Quantization. IEEE Trans. Inf. Theory 44(6), 2325–2383 (1998)

    Article  MATH  Google Scholar 

  33. Norouzi, M., Fleet, D.J.: Cartesian k-means. In: CVPR, pp. 3017–3024 (2013)

  34. Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: CVPR, pp. 817–824 (2011)

  35. Chan, W., Gupta, S., Gersho, A.: Enhanced multistage vector quantization by joint codebook design. IEEE Trans Commun 40(11), 1693–1697 (1992)

    Article  Google Scholar 

  36. Hwang, Y., Han, B., Ahn, H.: A fast nearest neighbor search algorithm by nonlinear embedding. In: International Conference on CVPR, pp. 2053–306 (2012)

  37. The ANN Evaluation Dataset. http://www.irisa.fr/texmex/people/jegou/ann.php

  38. Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: ECCV, pp. 304–317 (2008)

  39. The INRIA Holidays Dataset. http://lear.inrialpes.fr/people/jegou/data.php#holidays

  40. Torralba, A., Fergus, F., Freeman, W.T.: 80 million tiny images: a large database for non-parametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1958–1970 (2008)

    Article  Google Scholar 

  41. Babenko, A., Lempitsky V.: Additive quantization for extreme vector compression. In: CVPR, pp. 931–938 (2014)

  42. Zhang T., Du C., Wang J.: Composite quantization for approximate nearest neighbor search. In: ICML, pp. 1–9 (2014)

  43. Ai L., Yu J., Guan T., He Y.: Efficient approximate nearest neighbor search by optimized residual vector quantization. In: CBMI, pp. 1–4 (2014)

Download references

Acknowledgments

This paper is financially supported by the National Natural Science Foundation of China (NSFC) under Grant No. 61173114, 61202300, and 61272202.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China

    Liefu Ai, Junqing Yu, Zebin Wu, Yunfeng He & Tao Guan

  2. School of Computer and Information, Anqing Normal University, Anqing, 246133, China

    Liefu Ai

  3. Center of Network and Computation, Huazhong University of Science and Technology, Wuhan, 430074, China

    Junqing Yu

Authors
  1. Liefu Ai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Junqing Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zebin Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yunfeng He
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tao Guan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Junqing Yu.

Additional information

Communicated by T. Mei.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ai, L., Yu, J., Wu, Z. et al. Optimized residual vector quantization for efficient approximate nearest neighbor search. Multimedia Systems 23, 169–181 (2017). https://doi.org/10.1007/s00530-015-0470-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00530-015-0470-9

Keywords

Search

Navigation