Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning

Can Yüzkollar

doi:10.35377/saucis...1339150

EN

Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning

Abstract

Image hashing is an algorithm used to represent an image with a unique value. Hashing methods, which are generally developed to search for similar examples of an image, have gained a new dimension with the use of deep network structures and better results have started to be obtained with the methods. The developed deep network models generally consider hash functions independently and do not take into account the correlation between them. In addition, most of the existing data-dependent hashing methods use pairwise/triplet similarity metrics that capture data relationships from a local perspective. In this study, the Central similarity metric, which can achieve better results, is adapted to the deep reinforcement learning method with sequential learning strategy, and successful results are obtained in learning binary hash codes. By taking into account the errors of previous hash functions in the deep reinforcement learning strategy, a new model is presented that performs interrelated and central similarity based learning.

Keywords

References

[1] A. Swaminathan, Y. Mao and M. Wu, "Robust and secure image hashing," in IEEE Transactions on Information Forensics and Security, vol. 1, no. 2, pp. 215-230, June 2006, doi: 10.1109/TIFS.2006.873601.
[2] J. Wang, T. Zhang, N. Sebe, H. T. Shen et al., “A survey on learning to hash,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 769–790, 2018.
[3] S. Zhang, J. Li, M. Jiang, and B. Zhang, “Scalable discrete supervised multimedia hash learning with clustering,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. PP, no. 99, pp. 1–1, 2017.
[4] M. Kafai, K. Eshghi, and B. Bhanu, “Discrete cosine transform locality sensitive hashes for face retrieval,” IEEE Transactions on Multimedia (TMM), vol. 16, no. 4, pp. 1090–1103, 2014.
[5] P. Li, M. Wang, J. Cheng, C. Xu, and H. Lu, “Spectral hashing with semantically consistent graph for image indexing,” IEEE Transactions on Multimedia (TMM), vol. 15, no. 1, pp. 141–152, 2013.
[6] S. Zhang, J. Li, M. Jiang, and B. Zhang, “Scalable discrete supervised multimedia hash learning with clustering,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. PP, no. 99, pp. 1–1, 2017.
[7] V. E. Liong, J. Lu, Y.-P. Tan, and J. Zhou, “Deep video hashing,” IEEE Transactions on Multimedia (TMM), 2016.
[8] K. Ding, B. Fan, C. Huo, S. Xiang, and C. Pan, “Cross-modal hashing via rank-order preserving,” IEEE Transactions on Multimedia (TMM), vol. 19, no. 3, pp. 571–585, 2017.

[9] Z. Cao, M. Long, J. Wang, and S. Y. Philip. Hashnet: Deep learning to hash by continuation. In ICCV, pages 5609–5618, 2017.
[10] W.-J. Li, S. Wang, and W.-C. Kang. Feature learning based deep supervised hashing with pairwise labels. arXiv preprintrXiv:1511.03855, 2015.
[11] M. Norouzi, D. J. Fleet, and R. R. Salakhutdinov. Hamming distance metric learning. In Advances in neural information processing systems, pages 1061–1069, 2012.
[12] Yuan, L., Wang, T., Zhang, X., Tay, F. E., Jie, Z., Liu, W., & Feng, J. (2020). Central similarity quantization for efficient image and video retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3083-3092).
[13] Y. Li Deep reinforcement learning: An overview,2017
[14] Y. Peng, J. Zhang and Z. Ye, "Deep Reinforcement Learning for Image Hashing," in IEEE Transactions on Multimedia, vol. 22, no. 8, pp. 2061-2073, Aug. 2020, doi: 10.1109/TMM.2019.2951462.
[15] P. Indyk and R. Motwani. Approximate Nearest Neighbor {Towards Removing the Curse of Dimensionality. In Proceedings of the 30th Symposium on Theory of Computing, 1998, pp. 604{613.
[16] A. Gionis, P. Indyk, R. Motwani et al., “Similarity search in high dimensions via hashing,” in International Conference on Very Large Data Bases (VLDB), vol. 99, no. 6, 1999, pp. 518–529.
[17] M. Raginsky and S. Lazebnik, “Locality-sensitive binary codes from shift-invariant kernels,” in Annual Conference on Neural Information Processing Systems (NIPS), 2009, pp. 1509–1517.
[18] Y. Weiss, A. Torralba, and R. Fergus, “Spectral hashing,” in Annual Conference on Neural Information Processing Systems (NIPS), 2009, pp. 1753–1760.
[19] Y. Gong and S. Lazebnik, “Iterative quantization: A procrustean approach to learning binary codes,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, pp. 817–824.
[20] G. Irie, Z. Li, X.-M. Wu, and S.-F. Chang, “Locally linear hashing for extracting non-linear manifolds,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 2115–2122.
[21] Liu, W.; Mu, C.; Kumar, S.; and Chang, S. 2014. Discrete graph hashing. In NIPS, 3419–3427.
[22] Jiang, Q.-Y., and Li, W.-J. 2015. Scalable graph hashing with feature transformation. In IJCAI, 2248–2254.
[23] Liu, H.; Ji, R.; Wu, Y.; and Liu, W. 2016b. Towards optimal binary code learning via ordinal embedding. In AAAI, 1258–1265.
[24] X. Shen et al., “Semi-paired discrete hashing: Learning latent hash codesfor semi-paired cross-viewretrieval,” IEEE Trans. Cybern., vol. 47, no. 12,pp. 4275–4288, Dec. 2017.
[25] F. Shen, Y. Xu, L. Liu, Y. Yang, Z. Huang, and H. T. Shen, ``Unsupervised deep hashing with similarity-adaptive and discrete optimization,'' IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 12, pp. 30343044, Dec. 2018.
[26] X. Shen et al., “Multiview discrete hashing for scalable multimedia search,” ACM Trans. Intell. Syst. Technol., vol. 9, no. 5, pp. 1–21, 2018.
[27] Kong, W., and Li, W.-J. 2012. Isotropic hashing. In NIPS,1655–1663.
[28] R. Xia, Y. Pan, H. Lai, C. Liu, and S. Yan, “Supervised hashing for image retrieval via image representation learning,” in Proc. AAAI Conf. Artif.Intell., 2014, pp. 2156–2162.
[29] H. Lai,Y. Pan,Y. Liu, and S.Yan, “Simultaneous feature learning and hash coding with deep neural networks,” in Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2015, pp. 3270–3278.
[30] R. Zhang, L. Lin, R. Zhang, W. Zuo, and L. Zhang, “Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification,” IEEE Trans. Image Process., vol. 24, no. 12, pp. 4766–4779, Dec. 2015.
[31] H. Liu, R. Wang, S. Shan, and X. Chen, “Deep supervised hashing for fast image retrieval,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2064–2072.
[32] T. Yao, F. Long, T. Mei, and Y. Rui, “Deep semantic-preserving and ranking-based hashing for image retrieval,” in Proc. Int. Joint Conf. Artif. Intell., 2016, pp. 3931–3937.
[33] W.-J. Li, S. Wang, and W.-C. Kang, “Feature learning based deep supervised hashing with pairwise labels,” in Proc. Int. Joint Conf. Artif. Intell., 2016, pp. 1711–1717.
[34] Wu, L., Ling, H., Li, P., Chen, J., Fang, Y., & Zhou, F. (2019). Deep supervised hashing based on stable distribution. IEEE Access, 7, 36489-36499.
[35] L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement learning: A survey,” Journal of artificial intelligence research, vol. 4, pp. 237–285, 1996.

Details

Primary Language

English

Subjects

Software Engineering (Other)

Journal Section

Research Article

Authors

Can Yüzkollar ^*
0000-0001-5823-8773
Türkiye

Early Pub Date

August 31, 2023

Publication Date

August 31, 2023

Submission Date

August 7, 2023

Acceptance Date

August 31, 2023

Published in Issue

Year 2023 Volume: 6 Number: 2

DOI

https://doi.org/10.35377/saucis...1339150

IZ

https://izlik.org/JA95MS52LW

Cite

RIS / Bibtex

APA

Yüzkollar, C. (2023). Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning. Sakarya University Journal of Computer and Information Sciences, 6(2), 149-159. https://doi.org/10.35377/saucis...1339150

AMA

1.Yüzkollar C. Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning. SAUCIS. 2023;6(2):149-159. doi:10.35377/saucis.1339150

Chicago

Yüzkollar, Can. 2023. “Sequential and Correlated Image Hash Code Generation With Deep Reinforcement Learning”. Sakarya University Journal of Computer and Information Sciences 6 (2): 149-59. https://doi.org/10.35377/saucis. 1339150.

EndNote

Yüzkollar C (August 1, 2023) Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning. Sakarya University Journal of Computer and Information Sciences 6 2 149–159.

IEEE

[1]C. Yüzkollar, “Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning”, SAUCIS, vol. 6, no. 2, pp. 149–159, Aug. 2023, doi: 10.35377/saucis...1339150.

ISNAD

Yüzkollar, Can. “Sequential and Correlated Image Hash Code Generation With Deep Reinforcement Learning”. Sakarya University Journal of Computer and Information Sciences 6/2 (August 1, 2023): 149-159. https://doi.org/10.35377/saucis. 1339150.

JAMA

1.Yüzkollar C. Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning. SAUCIS. 2023;6:149–159.

MLA

Yüzkollar, Can. “Sequential and Correlated Image Hash Code Generation With Deep Reinforcement Learning”. Sakarya University Journal of Computer and Information Sciences, vol. 6, no. 2, Aug. 2023, pp. 149-5, doi:10.35377/saucis. 1339150.

Vancouver

1.Can Yüzkollar. Sequential and Correlated Image Hash Code Generation with Deep Reinforcement Learning. SAUCIS. 2023 Aug. 1;6(2):149-5. doi:10.35377/saucis. 1339150