Advertisement

Attention-Aware Invertible Hashing Network

  • Shanshan Li
  • Qiang Cai
  • Zhuangzi LiEmail author
  • Haisheng Li
  • Naiguang Zhang
  • Jian Cao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11903)

Abstract

In large-scale image retrieval tasks, hashing methods based on deep convolutional neural networks (CNNs) play an important role due to elaborate semantic feature representation. However, they usually progressively discard information during feature transformation, thus leading to incomplete and unsatisfactory hashing codes for image retrieval. This study tries to design an invertible architecture to maintain image information, meanwhile focus on necessary parts of image features. Consequently, in this paper, we propose a novel attention-aware invertible hashing network (AIHN) for image retrieval. By invertible feature representations, the final hash codes can be completely obtained from input images without any information loss. For highlighting informative regions, we present a novel attention-aware invertible block as the basic module of AIHN, which can promote generalization ability by spatial attention mechanism. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of our invertible feature representation on hash code generation, and show the promising performance on image retrieval of our methods against the state-of-the-arts.

Keywords

Image retrieval Deep hashing Attention mechanism 

Notes

Acknowledgement

This work was supported by National Key R&D Program of China (2018YFB0803700) and National Natural Science Foundation of China (61602517, 61877002).

References

  1. 1.
    Cao, Y., Long, M., Wang, J., Liu, S.: Collective deep quantization for efficient cross-modal retrieval. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  2. 2.
    Cao, Y., Long, M., Wang, J., Zhu, H., Wen, Q.: Deep quantization network for efficient image retrieval. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)Google Scholar
  3. 3.
    Cao, Z., Long, M., Wang, J., Yu, P.S.: Hashnet: deep learning to hash by continuation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5608–5617 (2017)Google Scholar
  4. 4.
    Donahue, J., et al.: Decaf: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647–655 (2014)Google Scholar
  5. 5.
    Gionis, A., Indyk, P., Motwani, R., et al.: Similarity search in high dimensions via hashing. In: VLDB, vol. 99, pp. 518–529 (1999)Google Scholar
  6. 6.
    Gomez, A.N., Ren, M., Urtasun, R., Grosse, R.B.: The reversible residual network: backpropagation without storing activations. In: Advances in Neural Information Processing Systems, pp. 2214–2224 (2017)Google Scholar
  7. 7.
    Gong, Y., Kumar, S., Rowley, H.A., Lazebnik, S.: Learning binary codes for high-dimensional data using bilinear projections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 484–491 (2013)Google Scholar
  8. 8.
    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)CrossRefGoogle Scholar
  9. 9.
    Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588–3597 (2018)Google Scholar
  10. 10.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)Google Scholar
  11. 11.
    Kulis, B., Darrell, T.: Learning to hash with binary reconstructive embeddings. In: Advances in Neural Information Processing Systems, pp. 1042–1050 (2009)Google Scholar
  12. 12.
    Lai, H., Pan, Y., Liu, Y., Yan, S.: Simultaneous feature learning and hash coding with deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3270–3278 (2015)Google Scholar
  13. 13.
    Li, C., Liu, Q., Liu, J., Lu, H.: Ordinal distance metric learning for image ranking. IEEE Trans. Neural Netw. Learn. Syst. 26(7), 1551–1559 (2014)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Li, C., Wang, X., Dong, W., Yan, J., Liu, Q., Zha, H.: Joint active learning with feature selection via cur matrix decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 41(6), 1382–1396 (2018)CrossRefGoogle Scholar
  15. 15.
    Li, C., Wei, F., Dong, W., Wang, X., Liu, Q., Zhang, X.: Dynamic structure embedded online multiple-output regression for streaming data. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 323–336 (2018)CrossRefGoogle Scholar
  16. 16.
    Li, W.J., Wang, S., Kang, W.C.: Feature learning based deep supervised hashing with pairwise labels. arXiv preprint arXiv:1511.03855 (2015)
  17. 17.
    Liu, H., Wang, R., Shan, S., Chen, X.: Deep supervised hashing for fast image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2064–2072 (2016)Google Scholar
  18. 18.
    Liu, W., Wang, J., Ji, R., Jiang, Y.G., Chang, S.F.: Supervised hashing with kernels. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2074–2081. IEEE (2012)Google Scholar
  19. 19.
    Liu, Y., Zhu, X., Zhao, X., Cao, Y.: Adversarial learning for constrained image splicing detection and localization based on atrous convolution. IEEE Trans. Inf. Forensics Secur. (2019) Google Scholar
  20. 20.
    Shen, F., Shen, C., Liu, W., Tao Shen, H.: Supervised discrete hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 37–45 (2015)Google Scholar
  21. 21.
    Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: Advances in Neural Information Processing Systems, pp. 1753–1760 (2009)Google Scholar
  22. 22.
    Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)Google Scholar
  23. 23.
    Yu, F., Kumar, S., Gong, Y., Chang, S.F.: Circulant binary embedding. In: International Conference on Machine Learning, pp. 946–954 (2014)Google Scholar
  24. 24.
    Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)
  25. 25.
    Zhang, P., Zhang, W., Li, W.J., Guo, M.: Supervised hashing with latent factor models. In: Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 173–182. ACM (2014)Google Scholar
  26. 26.
    Zhang, X.Y.: Simultaneous optimization for robust correlation estimation in partially observed social network. Neurocomputing 205, 455–462 (2016)CrossRefGoogle Scholar
  27. 27.
    Zhang, X.Y., Shi, H., Li, C., Zheng, K., Zhu, X., Duan, L.: Learning transferable self-attentive representations for action recognition in untrimmed videos with weak supervision. arXiv preprint arXiv:1902.07370 (2019)
  28. 28.
    Zhang, X.Y., Shi, H., Zhu, X., Li, P.: Active semi-supervised learning based onself-expressive correlation with generative adversarial networks. Neurocomputing 345, 103–113 (2019)CrossRefGoogle Scholar
  29. 29.
    Zhang, X.Y., Wang, S., Yun, X.: Bidirectional active learning: a two-way exploration into unlabeled and labeled data set. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 3034–3044 (2015)MathSciNetCrossRefGoogle Scholar
  30. 30.
    Zhang, X.Y., Wang, S., Zhu, X., Yun, X., Wu, G., Wang, Y.: Update vs. upgrade: modeling with indeterminate multi-class active learning. Neurocomputing 162, 163–170 (2015)CrossRefGoogle Scholar
  31. 31.
    Zhang, X.: Interactive patent classification based on multi-classifier fusion and active learning. Neurocomputing 127, 200–205 (2014)CrossRefGoogle Scholar
  32. 32.
    Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 294–310. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_18CrossRefGoogle Scholar
  33. 33.
    Zhu, H., Long, M., Wang, J., Cao, Y.: Deep hashing network for efficient similarity retrieval. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)Google Scholar
  34. 34.
    Zhu, X., Li, Z., Zhang, X.Y., Li, C., Liu, Y., Xue, Z.: Residual invertible spatio-temporal network for video super-resolution. In: AAAI Conference on Artificial Intelligence (2019)Google Scholar
  35. 35.
    Zhu, X., Li, Z., Zhang, X., Li, H., Xue, Z., Wang, L.: Generative adversarial image super-resolution through deep dense skip connections. In: Computer Graphics Forum, vol. 37, pp. 289–300. Wiley Online Library (2018)Google Scholar
  36. 36.
    Zhu, X., Liu, J., Wang, J., Li, C., Lu, H.: Sparse representation for robust abnormality detection in crowded scenes. Pattern Recogn. 47(5), 1791–1799 (2014)CrossRefGoogle Scholar
  37. 37.
    Zhu, X., Zhang, X., Zhang, X.Y., Xue, Z., Wang, L.: A novel framework for semantic segmentation with generative adversarial network. J. Vis. Commun. Image Represent. 58, 532–543 (2019)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Shanshan Li
    • 1
  • Qiang Cai
    • 1
  • Zhuangzi Li
    • 1
    Email author
  • Haisheng Li
    • 1
  • Naiguang Zhang
    • 2
  • Jian Cao
    • 1
  1. 1.School of Computer and Information EngineeringBeijing Technology and Business UniversityBeijingChina
  2. 2.Information Technology Institute, Academy of Broadcasting ScienceNRTABeijingChina

Personalised recommendations