Abstract
Hamming space retrieval enables efficient constant-time search through hash table lookups constructed by hash codes, where in response to each query, all data points within a small given Hamming radius are returned as relevant data. However, in Hamming space retrieval, the search performance of the existed hashing schemes based on linear scan dropped when the length of the hash codes increases. The reason is that the Hamming space becomes very sparse and it is difficult to pull the similar data into the Hamming ball and to push the dissimilar data outside the ball. Currently, the existing deep hashing methods based on hash table lookups pay too much attention to similar samples outside the ball and ignore the learning of dissimilar samples inside the ball, leading to a biased model. In this paper, we introduce discriminatory penalty into the exponential loss functions to optimize the Hamming space, leading to Exponential Hashing with Discriminatory Penalty (EHDP), which discriminately penalizes similar/dissimilar data inside and outside the Hamming ball. Technically, EHDP capitalizes on exponential function to discriminatively encourage similar/dissimilar data approaching/away and to up-weight/down-weight the dissimilar data inside/outside the ball. Extensive experiments demonstrate that the proposed EHDP obtains superior results on three benchmark datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, Y., Liu, B., Long, M., Wang, J.: Cross-modal hamming hashing. In: ECCV, pp. 202–218 (2018)
Cao, Y., Long, M., Liu, B., Wang, J.: Deep Cauchy hashing for hamming space retrieval. In: CVPR, pp. 1229–1237 (2018)
Cao, Z., Long, M., Wang, J., Yu, P.S.: HashNet: deep learning to hash by continuation. In: ICCV, pp. 5608–5617 (2017)
Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: Nus-wide: a real-world web image database from national university of Singapore. In: ICMR, pp. 1–9 (2009)
Fu, H., Li, Y., Zhang, H., Liu, J., Yao, T.: Rank-embedded hashing for large-scale image retrieval. In: ICMR, pp. 563–570 (2020)
Hu, W., Wu, L., Jian, M., Chen, Y., Yu, H.: Cosine metric supervised deep hashing with balanced similarity. Neurocomputing 448, 94–105 (2021)
Jiang, Q.Y., Li, W.J.: Asymmetric deep supervised hashing. In: AAAI, vol. 32 (2018)
Kang, R., Cao, Y., Long, M., Wang, J., Yu, P.S.: Maximum-margin hamming hashing. In: ICCV, pp. 8252–8261 (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS, pp. 1097–1105 (2012)
Li, Q., Sun, Z., He, R., Tan, T.: Deep supervised discrete hashing. In: NeurIPS, pp. 2482–2491 (2017)
Lin, M., Ji, R., Liu, H., Sun, X., Wu, Y., Wu, Y.: Towards optimal discrete online hashing with balanced similarity. In: AAAI, vol. 33, pp. 8722–8729 (2019)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, H., Wang, R., Shan, S., Chen, X.: Deep supervised hashing for fast image retrieval. In: CVPR, pp. 2064–2072 (2016)
Liu, H., Wang, R., Shan, S., Chen, X.: Learning multifunctional binary codes for both category and attribute oriented retrieval tasks. In: CVPR, pp. 3901–3910 (2017)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)
Su, S., Zhang, C., Han, K., Tian, Y.: Greedy hash: towards fast optimization for accurate hash coding in CNN. In: NeurIPS, pp. 798–807 (2018)
Wang, J., Zhang, T., Sebe, N., Shen, H.T., et al.: A survey on learning to hash. TPAMI 40(4), 769–790 (2017)
Wang, W., Shen, Y., Zhang, H., Yao, Y., Liu, L.: Set and rebase: determining the semantic graph connectivity for unsupervised cross modal hashing. In: IJCAI, pp. 853–859 (2020)
Wang, Y., Sun, Z.: Towards joint multiply semantics hashing for visual search. In: Zhao, Y., Barnes, N., Chen, B., Westermann, R., Kong, X., Lin, C. (eds.) ICIG 2019. LNCS, vol. 11903, pp. 47–58. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34113-8_5
Weng, Z., Zhu, Y.: Online hashing with efficient updating of binary codes. In: AAAI, vol. 34, pp. 12354–12361 (2020)
Xie, Y., Liu, Y., Wang, Y., Gao, L., Wang, P., Zhou, K.: Label-attended hashing for multi-label image retrieval. In: IJCAI, pp. 955–962 (2020)
Yan, C., Pang, G., Bai, X., Shen, C., Zhou, J., Hancock, E.: Deep hashing by discriminating hard examples. In: MM, pp. 1535–1542. ACM (2019)
Yang, G., Miao, H., Tang, J., Liang, D., Wang, N.: Multi-kernel hashing with semantic correlation maximization for cross-modal retrieval. In: Zhao, Y., Kong, X., Taubman, D. (eds.) ICIG 2017. LNCS, vol. 10666, pp. 23–34. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71607-7_3
Yuan, L., et al.: Central similarity quantization for efficient image and video retrieval. In: CVPR, pp. 3083–3092 (2020)
Zhu, H., Long, M., Wang, J., Cao, Y.: Deep hashing network for efficient similarity retrieval. In: AAAI, vol. 30 (2016)
Acknowledgements
This work was supported in part by Beijing Municipal Education Committee Science Foundation (KM201910005024), Beijing Postdoctoral Research Fundation (Q6042001202101).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, L., Chen, Y., Hu, W., Shi, G. (2021). Exponential Hashing with Different Penalty for Hamming Space Retrieval. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12888. Springer, Cham. https://doi.org/10.1007/978-3-030-87355-4_64
Download citation
DOI: https://doi.org/10.1007/978-3-030-87355-4_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87354-7
Online ISBN: 978-3-030-87355-4
eBook Packages: Computer ScienceComputer Science (R0)