Abstract
Deep supervised hashing aims to encode high-dimensional data into low-dimensional compact hash codes, which is important for solving large-scale image retrieval problems. In recent years, deep supervised hashing methods have achieved some positive outcomes. However, these methods can not meet expectations without fine-tuning from the off-the-shelf networks pre-trained on large-scale classification dataset. To cope with this problem, we rethink the paradigm of fine-tuning on deep supervised hashing and propose training deep supervised hashing from scratch. Based on this new perspective, we propose a wide residual hashing model trained from scratch, which can greatly improve the training time and reduce the model size. To the best of our knowledge, our method is the first framework that can train deep hashing networks from scratch without losing performance. By training from scratch, the parameters of the model are more less and our results are superior to state-of-the-art hashing algorithms. We hope the insights in this paper will open a new avenue for learning deep hash codes from scratch and transfer to further tasks not explored in this work.
This work was supported by the National Natural Science Foundation of China under Grant 61806220 and the Frontier Science and Technology Innovation Project of Army Engineering University of PLA.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Smeulders, A.W.M., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349–1380 (2000)
Zheng, L., Yang, Y., Tian, Q.: SIFT meets CNN: a decade survey of instance retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1224–1244 (2017)
Li, Y., Miao, Z., Wang, J., Zhang, Y.: Nonlinear embedding neural codes for visual instance retrieval. Neurocomputing 275, 1275–1281 (2018)
Zhang, X., Lai, H., Feng, J.: Attention-aware deep adversarial hashing for cross-modal retrieval. In: IEEE Conference on European Conference on Computer Vision, pp. 591–606 (2018)
Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: International Joint 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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3270–3278 (2015)
Zhu, H., Long, M., Wang, J., Cao, Y.: Deep hashing network for efficient similarity retrieval. In: International Conference on Artificial Intelligence, pp. 3270–3278 (2016)
Zhao, F., Huang, Y., Wang, L., Tan, T.: Deep semantic ranking based hashing for multi-label image retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1556–1564 (2015)
Zhang, R., Lin, L., Zhang, R., Zuo, W.: Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE Trans. Image Process. 24(12), 4766–4779 (2015)
Li, W.J., Wang, S., Kang, W.C.: Feature learning based deep supervised hashing with pairwise labels. In: International Joint Conference on Artificial Intelligence, pp. 1711–1717 (2015)
Wang, X., Shi, Y., Kitani, K.M.: Deep supervised hashing with triplet labels. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 70–84. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54181-5_5
Li, Y., Miao, Z., He, M., Zhang, Y., Li, H.: Deep attention residual hashing. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 101(3), 654–657 (2018)
Yang, H.F., Lin, K., Chen, C.S.: Supervised learning of semantics-preserving hash via deep convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 437–451 (2018)
Li, Y., Miao, Z., Wang, J., Zhang, Y.: Deep binary constraint hashing for fast image retrieval. Electron. Lett. 54(1), 25–27 (2018)
Gui, J., Liu, T., Sun, Z., Tao, D., Tan, T.: Fast supervised discrete hashing. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 490–496 (2017)
Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 817–824 (2011)
Wang, J., Zhang, T., Song, J., Sebe, N., Shen, H.T.: A survey on learning to hash. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 769–790 (2018)
Liong, V.E., Lu, J., Tan, Y.-P., Zhou, J.: Deep video hashing. IEEE Trans. Multimedia 19(6), 1209–1219 (2016)
Song, J., Zhang, H., Li, X., Gao, L., Wang, M., Hong, R.: Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Trans. Image Process. 27(7), 3210–3221 (2018)
Zhao, Y., Guangyuan, F., Wang, J., Guo, M., Guoxian, Yu.: Gene function prediction based on gene ontology hierarchy preserving hashing. Genomics 111(3), 334–342 (2019)
Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big data 3(1), 1–9 (2016). https://doi.org/10.1186/s40537-016-0043-6
Jie, L., Behbood, V., Hao, P., Zuo, H., Xue, S., Zhang, G.: Transfer learning using computational intelligence: a survey. Knowl.-Based Syst. 80, 14–23 (2015)
Guth, F., de Campos, T.E.: Research frontiers in transfer learning-a systematic and bibliometric review. arXiv preprint arXiv:1912.08812 (2019)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1106–1114 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, pp. 1–14 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? arXiv preprint arXiv:1902.10811 (2019)
Cao, Z., Long, M., Wang, J., Yu, P.S.: HashNet: deep learning to hash by continuation. In: IEEE International Conference on Computer Vision, pp. 5609–5618 (2018)
Cao, Y., Long, M., Liu, B., Wang, J.: Deep cauchy hashing for hamming space retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1229–1237 (2018)
Zhang, S., Li, J., Bo, Z.: Semantic cluster unary loss for efficient deep hashing. IEEE Trans. Image Process. 28(6), 1–17 (2019)
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Shen, Z., Liu, Z., Li, J., Jiang, Y.-G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: IEEE International Conference on Computer Vision, pp. 1919–1927 (2017)
Zhu, R., et al.: ScratchDet: training single-shot object detectors from scratch. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2268–2277 (2019)
de Masson d’Autume, C., Rosca, M., Rae, J.W., Mohamed, S.: Training language GANs from scratch. CoRR, abs/1905.09922 (2019)
Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 11–19 (2017)
He, K., Girshick, R.B., Dollár, P.: Rethinking imagenet pre-training. CoRR, abs/1811.08883 (2018)
Bethge, J., Yang, H., Bornstein, M., Meinel, C.: Back to simplicity: how to train accurate BNNs from scratch? arXiv preprint arXiv:1906.08637 (2019)
Zagoruyko, S., Komodakis, N.: Wide residual networks. In: IEEE Conference on British Machine Vision Conference, pp. 1–12 (2016)
Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., Le, Q.V.: Unsupervised data augmentation. arXiv preprint arXiv:1904.12848 (2019)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, pp. 1–15 (2015)
Song, J., He, T., Gao, L., Xu, X., Hanjalic, A., Shen, H.T.: Binary generative adversarial networks for image retrieval. In: Thirty-Second AAAI Conference on Artificial Intelligence, pp. 394–401 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y., Wang, J., Miao, Z., Wang, J., Zhang, R. (2020). Training Wide Residual Hashing from Scratch. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12307. Springer, Cham. https://doi.org/10.1007/978-3-030-60636-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-60636-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60635-0
Online ISBN: 978-3-030-60636-7
eBook Packages: Computer ScienceComputer Science (R0)