Abstract
Centralized aerial imagery analysis techniques face two challenges. The first one is the data silos problem, where data is located at different organizations separately. The second challenge is the class imbalance in the overall distribution of aerial scene data, due to the various collecting procedures across organizations. Federated learning (FL) is a method that allows multiple organizations to learn collaboratively from their local data without sharing. This preserves users’ privacy and tackles the data silos problem. However, traditional FL methods assume that the datasets are globally balanced, which is not realistic for aerial imagery applications. In this paper, we propose a Two-Stage FL framework (TS-FL), which mitigate the effect of the class imbalanced problem in aerial scene classification under FL. In particular, the framework introduces a feature representation method by combing supervised contrastive learning with knowledge distillation to enhance the model’s feature representation ability and minimize the client drift. Experiments on two public aerial datasets demonstrate that the proposed method outperforms other FL methods and possesses good generalization ability.
The work was supported in part by the National Natural Science Foundation of China under Grant 82172033, U19B2031, 61971369, 52105126, 82272071, 62271430, and the Fundamental Research Funds for the Central Universities 20720230104.
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
Alkhelaiwi, M., Boulila, W., Ahmad, J., Koubaa, A., Driss, M.: An efficient approach based on privacy-preserving deep learning for satellite image classification. Remote Sens. 13(11), 2221 (2021)
Chen, H.Y., Chao, W.L.: FedBE: making Bayesian model ensemble applicable to federated learning. arXiv preprint arXiv:2009.01974 (2020)
Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105(10), 1865–1883 (2017)
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)
Deng, Z., Liu, H., Wang, Y., Wang, C., Yu, Z., Sun, X.: PML: progressive margin loss for long-tailed age classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10503–10512 (2021)
He, C., et al.: FedML: a research library and benchmark for federated machine learning. arXiv preprint arXiv:2007.13518 (2020)
Ji, Z., Hou, L., Wang, X., Wang, G., Pang, Y.: Dual contrastive network for few-shot remote sensing image scene classification. IEEE Trans. Geosci. Remote Sens. 61, 1–12 (2023)
Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019)
Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., Suresh, A.T.: SCAFFOLD: stochastic controlled averaging for federated learning. In: International Conference on Machine Learning, pp. 5132–5143. PMLR (2020)
Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661–18673 (2020)
Li, Q., He, B., Song, D.: Model-contrastive federated learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10713–10722 (2021)
Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. Proc. Mach. Learn. Syst. 2, 429–450 (2020)
Li, Y., Lai, X., Wang, M., Zhang, X.: C-SASO: a clustering-based size-adaptive safer oversampling technique for imbalanced SAR ship classification. IEEE Trans. Geosci. Remote Sens. 60, 1–12 (2022)
McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Miao, W., Geng, J., Jiang, W.: Semi-supervised remote-sensing image scene classification using representation consistency siamese network. IEEE Trans. Geosci. Remote Sens. 60, 1–14 (2022)
Reddi, S., et al.: Adaptive federated optimization. arXiv preprint arXiv:2003.00295 (2020)
Sarkar, D., Narang, A., Rai, S.: Fed-focal loss for imbalanced data classification in federated learning. arXiv preprint arXiv:2011.06283 (2020)
Shi, J., Wu, T., Yu, H., Qin, A., Jeon, G., Lei, Y.: Multi-layer composite autoencoders for semi-supervised change detection in heterogeneous remote sensing images. SCIENCE CHINA Inf. Sci. 66(4), 140308 (2023)
Wang, J., Liu, Q., Liang, H., Joshi, G., Poor, H.V.: Tackling the objective inconsistency problem in heterogeneous federated optimization. Adv. Neural. Inf. Process. Syst. 33, 7611–7623 (2020)
Wang, L., Xu, S., Wang, X., Zhu, Q.: Addressing class imbalance in federated learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 10165–10173 (2021)
Xia, G.S., et al.: AID: a benchmark data set for performance evaluation of aerial scene classification. IEEE Trans. Geosci. Remote Sens. 55(7), 3965–3981 (2017)
Zhang, Y., Lei, Z., Yu, H., Zhuang, L.: Imbalanced high-resolution SAR ship recognition method based on a lightweight CNN. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)
Zhuang, Y., et al.: A hybrid framework based on classifier calibration for imbalanced aerial scene recognition. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds.) ICONIP 2022. LNCS, pp. 110–121. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-30111-7_10
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
Lv, Z., Zhuang, Y., Yang, G., Huang, Y., Ding, X. (2024). A Two-Stage Federated Learning Framework for Class Imbalance in Aerial Scene Classification. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14428. Springer, Singapore. https://doi.org/10.1007/978-981-99-8462-6_35
Download citation
DOI: https://doi.org/10.1007/978-981-99-8462-6_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8461-9
Online ISBN: 978-981-99-8462-6
eBook Packages: Computer ScienceComputer Science (R0)