Abstract
This article focuses on the challenge of classifying bronze inscription rubbings, which have a limited number of samples and diverse characteristics. Traditional classification methods have failed to produce satisfactory results. With the emergence of meta-learning, few-shot image classification has become a popular research topic. This approach allows a classifier to recognize datasets outside the training set and complete classification with only a small number of samples. However, due to the existence of multiple categories in the ancient inscription dataset and the tendency for overfitting, existing prototype network structures have not achieved satisfactory prediction accuracy on ancient inscription datasets. To address this challenge, we propose two strategies. The first strategy is the Margin Prototype (MP), which expands the distribution of different class prototypes during the softmax operation. The second strategy is the global information optimization strategy (GioP), which reverses the prediction of support set samples to obtain more representative prototypes. Our proposed method achieves better accuracy without adding new parameters to the model. The end-to-end structural pattern remains unchanged.
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
Ma, M., Mei, S., Wan, S., Hou, J., Wang, Z., Feng, D.D.: Video summarization via block sparse dictionary selection. Neurocomputing 378, 197–209 (2020)
Cheng, G., Yang, C., Yao, X., Guo, L., Han, J.: When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Trans. Geosci. Remote Sens. 56(5), 2811–2821 (2018)
Mei, S., Ji, J., Geng, Y., Zhang, Z., Li, X., Du, Q.: Unsupervised spatial-spectral feature learning by 3d convolutional autoencoder for hyperspectral classification. IEEE Trans. Geosci. Remote Sens. 57(9), 6808–6820 (2019)
Liu, Y., Suen, C.Y., Liu, Y., Ding, L.: Scene classification using hierarchical Wasserstein CNN. IEEE Trans. Geosci. Remote Sens. 57(5), 2494–2509 (2018)
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)
Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: Panet: few-shot image semantic segmentation with prototype alignment. In: proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9197–9206 (2019)
Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: International Conference on Machine Learning, pp. 1842–1850. PMLR (2016)
Zhang, S., Zhou, Z., Huang, Z., Wei, Z.: Few-shot classification on graphs with structural regularized GCNs (2019)
Munkhdalai, T., Yu, H.: Meta networks. In: International Conference on Machine Learning, pp. 2554–2563. PMLR (2017)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. arXiv preprint arXiv:1612.02295 (2016)
Cheng, G., et al.: SPnet: Siamese-prototype network for few-shot remote sensing image scene classification. IEEE Trans. Geosci. Remote Sens. 60, 1–11 (2021)
Liu, J., Song, L., Qin, Y.: Prototype rectification for few-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 741–756. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_43
Wang, J., Zhai, Y.: Prototypical Siamese networks for few-shot learning. In: 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC), pp. 178–181. IEEE (2020)
Koch, G., Zemel, R., Salakhutdinov, R., et al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2. Lille (2015)
Lake, B., Salakhutdinov, R., Gross, J., Tenenbaum, J.: One shot learning of simple visual concepts. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 33 (2011)
Ji, Z., Chai, X., Yu, Y., Pang, Y., Zhang, Z.: Improved prototypical networks for few-shot learning. Pattern Recogn. Lett. 140, 81–87 (2020)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, J., He, X., Liu, H., He, X. (2023). MGP-Net: Margin-Global Information Optimization-Prototype Network for Few-Shot Ancient Inscriptions Classification. In: Lu, H., et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14357. Springer, Cham. https://doi.org/10.1007/978-3-031-46311-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-46311-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46310-5
Online ISBN: 978-3-031-46311-2
eBook Packages: Computer ScienceComputer Science (R0)