Abstract
Hashing has been widely used in approximate nearest neighbor searching for large-scale image retrieval. Recently, many deep hashing methods have been proposed and significantly shown improved performance. However, most of these methods encode each image separately, ignoring that the images in the same set represent the same object or person. When used in large-scale scenes, they need to be compared one by one, which leads to poor retrieval performance. To solve this problem, we propose an unsupervised deep image set hashing method for multi-label image retrieval, which takes the image set as input, extracts image features and calculates set features, then constructs semantic structure through statistical information of features, and finally preserves this semantic structure through pair-wise loss function. Experiments show that our method has certain advantages on 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
Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In: 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS), pp. 21–24 (2006)
Kulis, B., Grauman, K.: Kernelized locality-sensitive hashing for scalable image search. In: 2009 IEEE 12th International Conference on Computer Vision (ICCV), pp. 2130–2137 (2009)
Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: Proceedings of the 21st International Conference on Neural Information Processing Systems (NIPS 2008), pp. 1753–1760 (2009)
Heo, J.-P., Lee, Y., He, J., Chang, S.-F., Yoon, S.-E.: Spherical hashing. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2957–2964 (2012)
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)
Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: Proceedings of the National Conference on Artificial Intelligence, pp. 2156–2162 (2014)
Lai, H., Pan, Y., Liu, Y., Yan, S.: Simultaneous feature learning and hash coding with deep neural networks. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3270–3278 (2015)
Lin, K., Yang, H., Hsiao, J., Chen, C.: Deep learning of binary hash codes for fast image retrieval. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 27–35 (2015)
Cao, Z., Long, M., Wang, J., Yu, P.S.: HashNet: deep learning to hash by continuation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5609–5618 (2017)
Lin, K., Lu, J., Chen, C., Zhou, J.: Learning compact binary descriptors with unsupervised deep neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1183–1192 (2016)
Yang, E., Deng, C., Liu, T., Liu, W., Tao, D.: Semantic structure-based unsupervised deep hashing. In: IJCAI, pp. 1064–1070 (2018)
Tu, R., Mao, X., Wei, W.: MLS3RDUH: deep unsupervised hashing via manifold based local semantic similarity structure reconstructing. In: IJCAI, pp. 3438–3444 (2020)
Liu, L., Rahimpour, A., Taalimi, A. Qi, H.: End-to-end binary representation learning via direct binary embedding. In: ICIP (2017)
Zhong, C., Yu, Y., Tang, S., Satoh, S., Xing, K.: Deep multi-label hashing for large-scale visual search based on semantic graph. In: Chen, L., Jensen, C.S., Shahabi, C., Yang, X., Lian, X. (eds.) APWeb-WAIM 2017. LNCS, vol. 10366, pp. 169–184. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63579-8_14
Wu, D., Lin, Z. Li, B., Ye, M., Wang, W.: Deep supervised hashing for multi-label and large-scale image retrieval. In Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval (ICMR 2017), pp. 150–158 (2017)
Zhang, Z., Zou, Q., Lin, Y., Chen, L., Wang, S.: Improved deep hashing with soft pairwise similarity for multi-label image retrieval. IEEE Trans. Multimedia 22(2), 540–553 (2019)
Chen, G., Cheng, X., Su, S., Tang, C.: Multiple-instance ranking based deep hashing for multi-label image retrieval. Neurocomputing 402, 89–99 (2020)
Feng, J., Karaman, S., Chang, S.: Deep image set hashing. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1241–1250 (2017)
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, N., Bai, C., Yang, Y. (2022). Unsupervised Deep Image Set Hashing for Efficient Multi-label Image Retrieval. In: Barolli, L. (eds) Innovative Mobile and Internet Services in Ubiquitous Computing. IMIS 2022. Lecture Notes in Networks and Systems, vol 496. Springer, Cham. https://doi.org/10.1007/978-3-031-08819-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-08819-3_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08818-6
Online ISBN: 978-3-031-08819-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)