Abstract
In large-scale retrieval, hash learning is favored by people owing to its fast speed. Nowadays, many hashing methods based on deep learning are proposed, because they have better performance than traditional feature representation methods. Both in supervised hash learning and unsupervised hash learning, similarity matrix is used in the objective function. In the similarity matrix, if two images share at least one label, the similarity is “1”, otherwise it is “0”. However, this kind of similarity can not reflect the similarity ranking of multi-label images well, which is vulnerable to pixel interference. Therefore, in order to improve the retrieval accuracy of multi-label data, we improve the traditional deep learning hashing method by dividing the multi-label images into “strong similarity” and “weak similarity”. In addition, although the deep neural network can judge the label of the images directly through the pixels, it does not understand the high-level semantics of the images. Hence, we take the feature invariance of the images into consideration, which means that the transformed image should have the same feature representation with the original image. In this way, we propose a novel Deep Hash learning method based on Feature-Invariant representation (FIDH), which focuses on deep understanding rather than deep learning. Experiments on common single-label and multi-label datasets show that our method obtains better performance than state-of-the-art methods in large-scale image retrieval.
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
Yi, J., Jiang, D., Sun, H., Zhao, X.: The research on nearest neighbor search algorithm based on vantage point tree. In: IEEE International Conference on Software Engineering and Service Science (2017)
Figueroa, K., Paredes, R.: Approximate direct and reverse nearest neighbor queries, and the k-nearest neighbor graph. In: International Workshop on Similarity Search and Applications, vol. 33, pp. 91–98 (2009)
Ke, Q., Ge, T., He, K., Sun, J.: Optimized product quantization for approximate nearest neighbor search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2946–2953. IEEE (2013)
Guan,T., Ai, L., Yu, J., He, Y.: Efficient approximate nearest neighbor search by optimized residual vector quantization. In: International Workshop on Content-Based Multimedia Indexing, pp. 1–4 (2014)
Cao, Y., Qi, H., Gui, J., Li, K., Tang, Y.Y., Kwok, J.T.: Learning to hash with dimension analysis based quantizer for image retrieval. 23, 3907–3918 (2021)
Lin, K., Yang, H., Chen, C.: Supervised learning of semantics-preserving hash via deep convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40, 437–451 (2018)
Li, Z., Xiao, F., Qi, G., Jin, L., Li, K., Tang, J.: Deep semantic-preserving ordinal hashing for cross-modal similarity search. IEEE Trans. Neural Netw. Learn. Syst. 30, 1429–1440 (2019)
Luo, X., Nie, L., Li, C., Yan, T., Xu, X.: Supervised robust discrete multimodal hashing for cross-media retrieval. IEEE Trans. Multimedia 21, 2863–2877 (2019)
Cui, X., Jiang, Q., Li, W.: Deep discrete supervised hashing. IEEE Trans. Multimedia 27, 5996–6009 (2018)
Wang, G., Moulin, P., Liong, V.E., Lu, J., Zhou, J.: Deep hashing for compact binary codes learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2475–2483 (2015)
Zhang, D., Lang, B., Liu, X., Mu, Y., Li, X.: Large-scale unsupervised hashing with shared structure learning. IEEE Trans. Cybern. 45, 1811–1822 (2015)
Liu, T., Li, J., Liu, W., Deng, C., Yang, E., Tao, D.: Unsupervised semantic-preserving adversarial hashing for image search. IEEE Trans. Image Process. 28, 4032–4044 (2019)
Peng, J., Xia, Z., Feng, X., Hadid, A.: Unsupervised deep hashing for large-scale visual search. In: International Conference on Image Processing Theory, Tools and Applications, pp. 1–5 (2016)
Li, Y., Zhu, Y., Wang, S.: Unsupervised deep hashing with adaptive feature learning for image retrieval. IEEE Signal Process. Lett. 26, 395–399 (2019)
Chen, C., Lin, K., Lu, J., Zhou, J.: Learning compact binary descriptors with unsupervised deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1183–1192 (2016)
Yang, P., Wang, S., Zhong, G., Xu, H., Dong, J.: Deep hashing learning networks. In: International Joint Conference on Neural Networks, pp. 2236–2243 (2016)
Hsiao, J., Lin, K., Yang, H., Chen, C.: Deep learning of binary hash codes for fast image retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 27–35 (2015)
Moreno, P.J., Carneiro, G., Chan, A.B., Vasconcelos, N.: Supervised learning of semantic classes for image annotation and retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 29, 394–410 (2007)
Wang, S., Li, W.W.: Feature learning based deep supervised hashing with pairwise labels (2015)
Liu, T., Wei, L., Yang, E., Deng, C., Tao, D.: Semantic structure-based unsupervised deep hashing. In: Twenty-Seventh International Joint Conference on Artificial Intelligence (2018)
Singh, P., Gidaris, S., Komodakis, N.: Unsupervised representation learning by predicting image rotations (2018)
Xu, C., Feng, Z., Tao, D.: Self-supervised representation learning by rotation feature decoupling. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10356–10366 (2019)
Li, B., Ye, M., Wu, D., Lin, Z., Wang, W.: Deep supervised hashing for multi-label and large-scale image retrieval. In: International Conference on Multimedia Retrieval, pp. 150–158 (2017)
Goodfellow, I., et al.: Generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Song, J.: Binary generative adversarial networks for image retrieval. Int. J. Comput. Vision 32, 1–22 (2020)
Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6706–6716 (2020)
Norouzi, M., Blei, D.M.: Minimal loss hashing for compact binary codes. In: International Conference on Machine Learning, pp. 353–360 (2011)
Ji, R., Jiang, Y.-G., Liu, W., Wang, J., Chang, S.-F.: Improved deep hashing with soft pairwise similarity for multi-label image retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2074–2081 (2012)
Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: CVPR, pp. 817–824 (2011)
Datar, M.: Locality-sensitive hashing scheme based on p-stable distributions (2004)
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles (2016)
Gupta, A., Doersch, C., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: IEEE International Conference on Computer Vision, pp. 1422–1430 (2015)
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, 540–553 (2020)
Wang, J., Zhu, H., Long, M., Cao, Y.: Deep hashing network for efficient similarity retrieval. In: AAAI Conference on Artificial Intelligence, pp. 2415–2421 (2016)
Huiskes, M.J., Lew, M.S.: The MIR Flickr retrieval evaluation. In: International Conference on Multimedia Retrieval, pp. 39–43 (2008)
Torralba, A., Weiss, Y., Fergus, R.: Spectral hashing. In: Advances in Neural Information Processing Systems, pp. 1753–1760 (2009)
Hsia, J.H., Lin, K., Yang, H.F., Chen, C. S.: deep learning of binary hash codes for fast image retrieval. In: Computer Vision and Pattern Recognition Workshops, pp. 27–35 (2015)
Wang, J., Cao, Z., Long, M., Yu, P. S.: HashNet: deep learning to hash by continuation. In: IEEE International Conference on Computer Vision, pp. 5609–5618 (2017)
Wang, J., Zhu, H., Cao, Y., Long, M., Wen, Q.: Deep quantization network for efficient image retrieval. In: AAAI Conference on Artificial Intelligence, pp. 3457–3463 (2016)
Ribeiro-Neto, B., Baeza-Yates, R.: Modern Information Retrieval. ACM Press, New York, 463 p. (1999)
He, J., Chang, S., Heo, J., Lee, Y., Yoon, S.: Spherical hashing: binary code embedding with hyperspheres. IEEE Trans. Pattern Anal. Mach. Intell. 11, 2304–2316 (2015)
Acknowledgment
This work is supported by the NSFC Grant No. 62202438; the Natural Science Foundation of Shandong Province Grant No. ZR2020QF041; the 22th batch of ISN Open Fund Grant No. ISN22-21.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Cao, Y., Shang, X., Liu, J., Qian, C., Chen, S. (2024). Deep Hash Learning of Feature-Invariant Representation for Single-Label and Multi-label Retrieval. In: Tari, Z., Li, K., Wu, H. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2023. Lecture Notes in Computer Science, vol 14487. Springer, Singapore. https://doi.org/10.1007/978-981-97-0834-5_2
Download citation
DOI: https://doi.org/10.1007/978-981-97-0834-5_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0833-8
Online ISBN: 978-981-97-0834-5
eBook Packages: Computer ScienceComputer Science (R0)