Abstract
In recent years, few-shot classification algorithms based on metric learning have gained significant attention in the field. However, in the context of cross-domain few-shot classification tasks, their performance still requires further improvement. To address this limitation, this paper proposes a cross-domain few-shot fine-grained classification model based on local-global semantic consistency. In order to tackle cross-domain few-shot classification challenges, we introduce a cross-loss computation method in this model. This method leverages the differences and similarities between global views and local views of each image, enabling the model to learn the local-global semantic consistency of the images. Through this approach, the model can capture shared features across different domains, thereby reducing intra-feature semantic differences and enhancing the consistency of class relationships in sample predictions. Building on the comprehensive utilization of local and global features in images, our model excels at focusing on local details closely related to specific categories. This further strengthens intra-class associations among similar images, leading to more effective discrimination of fine-grained categories. In summary, our proposed cross-domain few-shot fine-grained classification model, based on local-global semantic consistency, not only aims to address the challenges of metric learning in cross-domain few-shot classification but also provides a promising approach for fine-grained classification tasks.
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
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. Advances in neural information processing systems. 30 (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)
Zhou, F., Wang, P., Zhang, L., Wei, W., Zhang, Y.: Revisiting prototypical network for cross domain few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20061–20070 (2023)
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vision 40, 99–121 (2000)
Li, W., Wang, L., Xu, J., Huo, J., Gao, Y., Luo, J.: Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7260–7268 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Zhang, C., Cai, Y., Lin, G., Shen, C.: Deepemd: few-shot image classification with differentiable earth mover's distance and structured classifiers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020, pp. 12203–12213 (2020)
Chen, Z., Fu, Y., Zhang, Y., Jiang, Y.G., Xue, X., Sigal, L.: Multi-level semantic feature augmentation for one-shot learning. IEEE Trans. Image Process. 28(9), 4594–4605 (2019)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: International Conference on Learning Representations, 4 November 2016
Wertheimer, D., Tang, L., Hariharan, B.: Few-shot classification with feature map reconstruction networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8012–8021 (2021)
Boney, R., Ilin, A.: Semi-supervised few-shot learning with MAML
Li, P., Gong, S., Wang, C., Fu, Y.: Ranking distance calibration for cross-domain few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022, pp. 9099–9108 (2022)
Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999, 8 Mar 2018
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10657–10665 (2019)
Garcia, V., Bruna, J.: Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043, 10 November 2017
Das, D., Yun, S., Porikli, F.: ConfeSS: a framework for single source cross-domain few-shot learning. In: International Conference on Learning Representations 6 Oct 2021
Liang, H., Zhang, Q., Dai, P., Lu, J.: Boosting the generalization capability in cross-domain few-shot learning via noise-enhanced supervised autoencoder. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9424–9434 (2021)
Tseng, H.Y., Lee, H.Y., Huang, J.B., Yang, M.H.: Cross-domain few-shot classification via learned feature-wise transformation. arXiv preprint arXiv:2001.08735, 23 Jan 2020
Wang, C., Chan, S.C.: A new hand gesture recognition algorithm based on joint color-depth superpixel earth mover's distance. In: 2014 4th International Workshop on Cognitive Information Processing (CIP), pp. 1–6. IEEE, 26 May 2014
Guo, Y., et al.: A broader study of cross-domain few-shot learning. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVII 16 2020, pp. 124–141. Springer, Cham (2020)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D.: Matching networks for one shot learning. Advances in neural information processing systems 29 (2016)
Xu, H., Zhi, S., Sun, S., Patel, V.M., Liu, L.: Deep learning for cross-domain few-shot visual recognition: A survey. arXiv preprint arXiv:2303.08557, 15 March 2023
Hu, Y., Ma, A.J.: Adversarial feature augmentation for cross-domain few-shot classification. In: European Conference on Computer Vision 2022 Oct 20, pp. 20–37. Cham: Springer Nature Switzerland
Wertheimer, D., Hariharan, B.: Few-shot learning with localization in realistic settings. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019, pp. 6558–6567 (2019)
Yao, H., et al.: Graph few-shot learning via knowledge transfer. In: Proceedings of the AAAI Conference on Artificial Intelligence 2020 Apr 3, vol. 34, No. 04, pp. 6656–6663 (2020)
Li, H., Pan, S.J., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, pp. 5400–5409 (2018)
Hu, Z., Sun, Y., Yang, Y.: Switch to generalize: domain-switch learning for cross-domain few-shot classification. In: International Conference on Learning Representations 2021 Oct 6
Zou, Y., Liu, Y., Hu, Y., Li, Y., Li, R.: Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning. arXiv preprint arXiv:2403.00567, 1 Mar 2024
Nakamura, A., Harada, T.: Revisiting fine-tuning for few-shot learning. arXiv preprint arXiv:1910.00216, 1 Oct 2019
Shen, W., Shi, Z., Sun, J.: Learning from adversarial features for few-shot classification. arXiv preprint arXiv:1903.10225, 25 March 2019
Acknowledgments
This work was financially supported by the Natural Science Foundation of China (No. 61662034 and No. 62266022), the Natural Science Foundation of Jiangxi Province(20202BAB202020) and the Jiangxi Double Thousand Plan (JXSQ2019101077).
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
Chen, T., Liu, J., Wei, H., Liu, X., Li, C. (2024). Cross-Domain Few-Shot Fine-Grained Classification Based on Local-Global Semantic Consistency and Earth Mover’s Distance. In: Huang, DS., Zhang, X., Guo, J. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2024. Lecture Notes in Computer Science, vol 14866. Springer, Singapore. https://doi.org/10.1007/978-981-97-5594-3_24
Download citation
DOI: https://doi.org/10.1007/978-981-97-5594-3_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5593-6
Online ISBN: 978-981-97-5594-3
eBook Packages: Computer ScienceComputer Science (R0)