Abstract
Long-tailed hashing is to learn hash functions in unbalanced distribution datasets to represent images as binary hash codes for fast and accurate image retrieval. In contrast to balanced distribution datasets, unbalanced distributions are more common in the real world. However, Existing long-tailed hashing methods only focus on how to better learn from unbalanced datasets to improve performance, without giving good consideration to quantization error, which is very crucial in hash learning. In this paper, we propose a simple but efficient quantization method for long-tailed hashing. Specifically, to address the lack of samples in the tail classes, we take a uniform discrete distribution as the optimal target distribution. We use the Sliced Wasserstein distance as a measure of distribution distance. It makes good use of the discrete nature of hash functions and has low computational complexity. Then we formulate the optimization objective of the quantization error as minimizing the distance between the output of the learned hash function and this objective distribution, which can be added as an additional term of the loss function to existing long-tailed hashing methods. We conduct experiments on two long-tailed datasets, and the results show that our proposed method greatly improves the performance of existing long-tailed hashing methods.
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
Similar content being viewed by others
References
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: International Conference on Learning Representations (2017)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International conference on machine learning. pp. 214–223. PMLR (2017)
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)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research 16, 321–357 (2002)
Chen, Y., Hou, Y., Leng, S., Zhang, Q., Lin, Z., Zhang, D.: Long-tail hashing. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1328–1338 (2021)
Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 9268–9277 (2019)
Deshpande, I., Zhang, Z., Schwing, A.G.: Generative modeling using the sliced wasserstein distance. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3483–3491 (2018)
Doan, K.D., Manchanda, S., Mahapatra, S., Reddy, C.K.: Interpretable graph similarity computation via differentiable optimal alignment of node embeddings. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 665–674 (2021)
He, J., Chang, S.F., Radhakrishnan, R., Bauer, C.: Compact hashing with joint optimization of search accuracy and time. In: CVPR 2011. pp. 753–760. IEEE (2011)
Huang, C.Q., Yang, S.M., Pan, Y., Lai, H.J.: Object-location-aware hashing for multi-label image retrieval via automatic mask learning. IEEE Trans. Image Process. 27(9), 4490–4502 (2018)
Kang, Q., Chen, X., Li, S., Zhou, M.: A noise-filtered under-sampling scheme for imbalanced classification. IEEE transactions on cybernetics 47(12), 4263–4274 (2016)
Kolouri, S., Nadjahi, K., Simsekli, U., Badeau, R., Rohde, G.: Generalized sliced wasserstein distances. Advances in neural information processing systems 32 (2019)
Kou, X., Xu, C., Yang, X., Deng, C.: Attention-guided contrastive hashing for long-tailed image retrieval. In: IJCAI. pp. 1017–1023 (2022)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
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)
Lai, H., Yan, P., Shu, X., Wei, Y., Yan, S.: Instance-aware hashing for multi-label image retrieval. IEEE Trans. Image Process. 25(6), 2469–2479 (2016)
Li, Q., Sun, Z., He, R., Tan, T.: Deep supervised discrete hashing. Advances in neural information processing systems 30 (2017)
Li, W.J., Wang, S., Kang, W.C.: Feature learning based deep supervised hashing with pairwise labels. In: IJCAI. pp. 1711–1717 (2016)
Liang, Y., Pan, Y., Lai, H., Liu, W., Yin, J.: Deep listwise triplet hashing for fine-grained image retrieval. IEEE Trans. Image Process. 31, 949–961 (2021)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp. 2980–2988 (2017)
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)
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 2537–2546 (2019)
Nguyen, K., Ho, N., Pham, T., Bui, H.: Distributional sliced-wasserstein and applications to generative modeling. arXiv preprint arXiv:2002.07367 (2020)
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)
Wang, L., Pan, Y., Liu, C., Lai, H., Yin, J., Liu, Y.: Deep hashing with minimal-distance-separated hash centers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 23455–23464 (2023)
Wang, Y.X., Ramanan, D., Hebert, M.: Learning to model the tail. Advances in neural information processing systems 30 (2017)
Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. Advances in neural information processing systems 21 (2008)
Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: Proceedings of the AAAI conference on artificial intelligence. vol. 28 (2014)
Yuan, L., Wang, T., Zhang, X., Tay, F.E., Jie, Z., Liu, W., Feng, J.: 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 (2020)
Acknowledgements
This work was supported by Guangdong Basic and Applied Basic Research Foundation (2023A1515011400). The corresponding author is Yan Pan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fu, Z., Lai, H., Pan, Y. (2025). Long-Tailed Hashing with Wasserstein Quantization. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15321. Springer, Cham. https://doi.org/10.1007/978-3-031-78305-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-78305-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78304-3
Online ISBN: 978-3-031-78305-0
eBook Packages: Computer ScienceComputer Science (R0)
