Skip to main content
SpringerLink
Log in

Semantic-guided hashing learning for domain adaptive retrieval

  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

Recently, domain adaptive retrieval has aroused much attention. However, most existing methods are proposed under the single-domain assumption. They neglect two issues: a) the data distribution discrepancy between the retrieved set (source domain) and query set (target domain); and b) the semantic discrepancy between the features and labels. In this work, we propose a novel transferable hashing method to address these two issues, termed Semantic-Guided Hashing Learning (SGHL). First, the marginal and conditional distributions between the source and target domains are aligned to reduce the distribution discrepancy between the two domains. Then, we embed the semantic information of the source domain into a latent semantic space to alleviate the semantic discrepancy between the features and labels. Moreover, linear embedding is explored with orthogonal transformation to minimize the quantization loss between the latent semantic space and Hamming space. At last, an iterative algorithm is designed to generate hash codes directly. Extensive experiments on four widely-used cross-domain retrieval datasets demonstrate that SGHL outperforms the state-of-art hashing methods.

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

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7

Similar content being viewed by others

Notes

  1. In this paper, we use ”features” to denote the visual properties of a sample, which is the natural property carried by the sample, e.g., the colors of a images. By contrast, we use ”labels” to present the semantic information of a sample, and it is mostly defined by humans, e.g., a cookware used to fry food is called ”pan” (and ”pan” is a semantic description).

References

  1. Shen, F., Shen, C., Liu, W., Shen, H.T.: Supervised Discrete Hashing. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 37–45. https://doi.org/10.1109/CVPR.2015.7298598 (2015)

  2. Fang, X., Liu, Z., Han, N., Jiang, L., Teng, S.: Discrete matrix factorization hashing for cross-modal retrieval. Int. J. Mach. Learn. Cybern. 12(10), 3023–3036 (2021). https://doi.org/10.1007/s13042-021-01395-5

    Article  Google Scholar 

  3. Cui, Y., Jiang, J., Lai, Z., Hu, Z., Wong, W.: Supervised discrete discriminant hashing for image retrieval. Pattern Recognit. 78, 79–90 (2018)

    Article  Google Scholar 

  4. Shen, F., Yang, Y., Liu, L., Liu, W., Tao, D., Shen, H.T.: Asymmetric binary coding for image search. IEEE Trans. Multimedia 19(9), 2022–2032 (2017). https://doi.org/10.1109/tmm.2017.2699863

    Article  Google Scholar 

  5. Li, Z., Tang, J., Zhang, L., Yang, J.: Weakly-supervised semantic guided hashing for social image retrieval. Int. J. Comput. Vis. 128(8-9), 2265–2278 (2020). https://doi.org/10.1007/s11263-020-01331-0

    Article  MathSciNet  MATH  Google Scholar 

  6. Lin, M., Ji, R., Chen, S., Sun, X., Lin, C.W.: Similarity-preserving linkage hashing for online image retrieval. IEEE Trans. Image Process. 29, 5289–5300 (2020). https://doi.org/10.1109/TIP.2020.2981879

    Article  MathSciNet  MATH  Google Scholar 

  7. Teng, S., Zheng, Z., Wu, N., Fei, L., Zhang, W.: Domain adaptation via incremental confidence samples into classification. Int. J. Intell. Syst. 37 (1), 365–385 (2021). https://doi.org/10.1002/int.22629

    Article  Google Scholar 

  8. Huang, F., Zhang, L., Yang, Y., Zhou, X.: Probability weighted compact feature for domain adaptive retrieval. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9582–9591. https://doi.org/10.1109/CVPR42600.2020.00960(2020)

  9. Huang, F., Zhang, L., Gao, X.: Domain adaptation preconceived hashing for unconstrained visual retrieval. IEEE Trans. Neural Netw. Learn. Syst. 1–15. https://doi.org/10.1109/TNNLS.2021.3071127 (2021)

  10. Liu, W., Wang, J., Ji, R., Jiang, Y.-G., Chang, S.-F.: Supervised hashing with kernels. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2074–2081. https://doi.org/10.1109/CVPR.2012.6247912 (2012)

  11. Datar, M., Immorlica, N., Indyk, P., Mirrokni, V.S.: Locality-sensitive hashing scheme based on p-stable distributions. In: The Twentieth Annual Symposium on Computational Geometry, pp. 253–262. https://doi.org/10.1145/997817.997857 (2004)

  12. Shi, X., Xing, F., Xu, K., Sapkota, M., Yang, L.: Aaai: asymmetric discrete graph hashing. In: 31St AAAI Conference on Artificial Intelligence, pp. 2541–2547 (2017)

  13. Gong, Y., Lazebnik, S., Gordo, A., Perronnin, F.: Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2916–2929 (2013). https://doi.org/10.1109/TPAMI.2012.193

    Article  Google Scholar 

  14. Mengqiu, H., Yang, Y., Fumin, S., Ning, X., Heng Tao, S.: Hashing with angular reconstructive embeddings. IEEE Trans. Image Process. 27 (2), 545–555 (2018). https://doi.org/10.1109/TIP.2017.2749147

    Article  MathSciNet  MATH  Google Scholar 

  15. Wang, L., Yang, J., Zareapoor, M., Zheng, Z.: Cluster-wise unsupervised hashing for cross-modal similarity search. Pattern Recognit. 111, 107732 (2021). https://doi.org/10.1016/j.patcog.2020.107732

    Article  Google Scholar 

  16. Fang, Y., Li, B., Li, X., Ren, Y.: Unsupervised cross-modal similarity via latent structure discrete hashing factorization. Knowl. Based Syst. 218. https://doi.org/10.1016/j.knosys.2021.106857 (2021)

  17. Zhang, Z., Lai, Z., Huang, Z., Wong, W.K., Xie, G.-S., Liu, L., Shao, L.: Scalable supervised asymmetric hashing with semantic and latent factor embedding. IEEE Trans. Image Process. 28(10), 4803–4818 (2019). https://doi.org/10.1109/TIP.2019.2912290

    Article  MathSciNet  MATH  Google Scholar 

  18. Chen, Y., Tian, Z., Zhang, H., Wang, J., Zhang, D.: Strongly constrained discrete hashing. IEEE Trans. Image Process. 29, 3596–3611 (2020). https://doi.org/10.1109/TIP.2020.2963952

    Article  MathSciNet  MATH  Google Scholar 

  19. Luo, X., Nie, L., He, X., Wu, Y., Chen, Z.-D., Xu, X -S.: Fast scalable supervised hashing. In: The 41St International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 735–744. https://doi.org/10.1145/3209978.3210035 (2018)

  20. Huang, J., Feris, R., Chen, Q., Yan, S.: Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network. In: IEEE International Conference on Computer Vision, pp. 1062–1070. https://doi.org/10.1109/ICCV.2015.127 (2015)

  21. Ji, X., Wang, W., Zhang, M., Yang, Y.: Cross-domain image retrieval with attention modeling. In: The 25Th ACM International Conference on Multimedia, pp. 1654–1662. https://doi.org/10.1145/3123266.3123429 (2017)

  22. Zhang, L., Liu, J., Yang, Y., Huang, F., Nie, F., Zhang, D.: Optimal projection guided transfer hashing for image retrieval. IEEE Trans. Circuits Syst. Video Technol. 30(10), 3788–3802 (2020). https://doi.org/10.1109/tcsvt.2019.2943902

    Article  Google Scholar 

  23. Wang, J., Chen, Y., Hao, S., Feng, W., Shen, Z.: Balanced distribution adaptation for transfer learning. In: IEEE International Conference on Data Mining, pp. 1129–1134. https://doi.org/10.1109/ICDM.2017.150 (2017)

  24. Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. Learn. Syst. 22 (2), 199–210 (2011). https://doi.org/10.1109/tnn.2010.2091281

    Article  Google Scholar 

  25. Schönemann, P. H.: A generalized solution of the orthogonal procrustes problem. Psychometrika 31(1), 1–10 (1966). https://doi.org/10.1109/TIP.2018.2863040

    Article  MathSciNet  MATH  Google Scholar 

  26. Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: the 21st International Conference on Neural Information Processing Systems. Curran Associates Inc, pp. 1753–1760 (2008)

  27. Liu, H., Ji, R., Wang, J., Shen, C.: Ordinal constraint binary coding for approximate nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 941–955 (2019). https://doi.org/10.1109/TPAMI.2018.2819978

    Article  Google Scholar 

  28. Zhou, J.T., Zhao, H., Peng, X., Fang, M., Qin, Z., Goh, R.S.M.: Transfer hashing: from shallow to deep. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 6191–6201 (2018). https://doi.org/10.1109/TNNLS.2018.2827036

    Article  Google Scholar 

  29. Jin, Z., Li, C., Lin, Y., Cai, D.: Density sensitive hashing. IEEE Trans. Cybern. 44(8), 1362–71 (2014). https://doi.org/10.1109/TCYB.2013.2283497

    Article  Google Scholar 

  30. Jiang, Q.-Y., Li, W.-J.: Scalable graph hashing with feature transformation. In: The 24Th International Conference on Artificial Intelligence, pp. 2248–2254 (2015)

  31. Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791

    Article  Google Scholar 

  32. Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 550–554 (1994). https://doi.org/10.1109/34.29144

    Article  Google Scholar 

  33. Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1521–1528. https://doi.org/10.1109/CVPR.2011.5995347 (2011)

  34. Daumé, H. III: Frustratingly easy domain adaptation. In: The 45Th Annual Meeting of the Association of Computational Linguistics, pp. 256–263 (2007)

  35. Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5385–5394. https://doi.org/10.1109/CVPR.2017.572(2017)

  36. Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: IEEE International Conference on Computer Vision, pp. 2200–2207. https://doi.org/10.1109/iccv.2013.274 (2013)

  37. Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: a deep convolutional activation feature for generic visual recognition. In: The 31St International Conference on Machine Learning, pp. 647–655 (2014)

  38. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)

  39. Ringwald, T., Stiefelhagen, R.: Adaptiope: a modern benchmark for unsupervised domain adaptation. In: The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 101–110 (2021)

  40. Bo, H., Tongliang, Q.Y., Liu, G.N., Ivor W., Tsang, J.T.K., Sugiyama, M.: A survey of label-noise representation learning: Past, present and future. arXiv:2011.04406 (2020)

Download references

Acknowledgements

This work is supported in part by the Key-Area Research and Development Program of Guangdong Province under Grant 2020B010166006, and by the National Natural Science Foundation of China under Grant 61972102.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006, China

    Wei Zhang, Xiaoqiong Yang & Shaohua Teng

  2. Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems, Macau University of Science and Technology, Macao, 999078, China

    NaiQi Wu

Authors
  1. Wei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoqiong Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shaohua Teng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. NaiQi Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shaohua Teng.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, W., Yang, X., Teng, S. et al. Semantic-guided hashing learning for domain adaptive retrieval. World Wide Web 26, 1093–1112 (2023). https://doi.org/10.1007/s11280-022-01072-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11280-022-01072-9

Keywords

Search

Navigation