Advertisement

Triple-Bit Quantization with Asymmetric Distance for Nearest Neighbor Search

  • Han Deng
  • Hongtao XieEmail author
  • Wei Ma
  • Qiong Dai
  • Jianjun Chen
  • Ming Lu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9917)

Abstract

Binary embedding is an effective way for nearest neighbor (NN) search as binary code is storage efficient and fast to compute. It tries to convert real-value signatures into binary codes while preserving similarity of the original data, and most binary embedding methods quantize each projected dimension to one bit (presented as 0/1). As a consequence, it greatly decreases the discriminability of original signatures. In this paper, we first propose a novel quantization strategy triple-bit quantization (TBQ) to solve the problem by assigning 3-bit to each dimension. Then, asymmetric distance (AD) algorithm is applied to re-rank candidates obtained from hamming space for the final nearest neighbors. For simplicity, we call the framework triple-bit quantization with asymmetric distance (TBAD). The inherence of TBAD is combining the best of binary codes and real-value signatures to get nearest neighbors quickly and concisely. Moreover, TBAD is applicable to a wide variety of embedding techniques. Experimental comparisons on BIGANN set show that the proposed method can achieve remarkable improvement in query accuracy compared to original binary embedding methods.

Keywords

Triple-bit quantization Asymmetric distance Binary embedding Nearest neighbor search 

Notes

Acknowledgements

This work is supported by the National Nature Science Foundation of China (61303171, 61303251), the “Strategic Priority Research Program” of the Chinese Academy of Sciences (XDA06031000, XDA06010703), Xinjiang Uygur Autonomous Region Science and Technology Project (201230123).

References

  1. 1.
    Yahiaoui, I., Hervé, N., Boujemaa, N.: Shape-based image retrieval in botanical collections. In: Proceedings of the 7th PCM 2006, China, 2–4 November 2006, pp. 357–364 (2006)Google Scholar
  2. 2.
    Megrhi, S., Souidène, W., Beghdadi, A.: Spatio-temporal SURF for human action recognition. In: Huet, B., Ngo, C.-W., Tang, J., Zhou, Z.-H., Hauptmann, Alexander, G., Yan, S. (eds.) PCM 2013. LNCS, vol. 8294, pp. 505–516. Springer, Heidelberg (2013). doi: 10.1007/978-3-319-03731-8_47 CrossRefGoogle Scholar
  3. 3.
    Chen, S., Wang, T., Wang, J., Li, J., Zhang, Y., Lu, H.: A spatial-temporal-scale registration approach for video copy detection. In: Huang, Y.-M.R., Xu, C., Cheng, K.-S., Yang, J.-F.K., Swamy, M.,N.,S., Li, S., Ding, J.-W. (eds.) PCM 2008. LNCS, vol. 5353, pp. 407–415. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-89796-5_42 CrossRefGoogle Scholar
  4. 4.
    Albert, G., Florent, P., Yunchao, G., et al.: Asymmetric distances for binary embeddings. IEEE PAMI 36(1), 33–47 (2014)CrossRefGoogle Scholar
  5. 5.
    Raginsky, M., Lazebnik, S.: Locality-sensitive binary codes from shift-invariant kernels. In: Proceedings of NIPS, pp. 1509–1517 (2009)Google Scholar
  6. 6.
    Jégou, H., Tavenard, R., Douze, M., Amsaleg, L.: Searching in one billion vectors: re-rank with source coding. In: IEEE ICASSP, pp. 861–864. IEEE (2011)Google Scholar
  7. 7.
    Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: Proceedings of NIPS (2008)Google Scholar
  8. 8.
    Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: Proceedings of IEEE Conference on CVPR, pp. 817–824 (2011)Google Scholar
  9. 9.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  10. 10.
    Xie, H., Gao, K., Zhang, Y., et al.: Pairwise weak geometric consistency for large scale image search. In: Proceedings of the 1st ACM ICMR, pp. 1–8. ACM (2011)Google Scholar
  11. 11.
    Lei, Z., Yongdong, Z., Richang, H., et al.: Full-space local topology extraction for cross-modal retrieval. IEEE TIP 24(7), 2212–2224 (2015)MathSciNetGoogle Scholar
  12. 12.
    Yahiaoui, I., Hervé, N., Boujemaa, N.: Shape-based image retrieval in botanical collections. In: Advances in Multimedia Information Processing – 7th PCM 2006, Hangzhou, China, 2–4 November 2006, pp. 357–364 (2006)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Han Deng
    • 1
  • Hongtao Xie
    • 1
    Email author
  • Wei Ma
    • 1
  • Qiong Dai
    • 1
  • Jianjun Chen
    • 1
    • 2
  • Ming Lu
    • 3
  1. 1.National Engineering Laboratory for Information Security TechnologiesInstitute of Information Engineering, Chinese Academy of SciencesBeijingChina
  2. 2.School of Computer and Communication EngineeringChangsha University of Science and TechnologyChangshaChina
  3. 3.School of Information EngineeringHeNan Radio and Television UniversityZhengzhouChina

Personalised recommendations