Abstract
The performance of scene classification for remote sensing images based on deep neural networks is limited by the number of labeled data. To alleviate this problem, a variety of methods have been proposed to apply semi-supervised learning to exploit both labeled and unlabeled samples for training classifiers, but most of them still require a certain number of labeled samples considering the complex context relationship and huge spatial differences of remote sensing images. In this paper, we proposed a novel selected sample retraining semi-supervised learning method (S\(^2\)R) that is simple but works efficiently on scene classification remote sensing. First, we train several models independently, each model is trained for only a few epochs, and use them to label samples in the unlabeled data set. Then, the labeled unlabeled data set is divided into low-noise labeled data set and sub-unlabeled data set through the high probability sample selection method. Finally, the two segmented data sets are combined with the labeled data sets to train a scene classifier based on the semi-supervised learning method. To verify the effectiveness of the proposed method, it is further compared with several state-of-the-art semi-supervised classification approaches. The results demonstrate that our method consistently outperforms the previous methods on the condition of only a few labeled samples over the scene classification for remote sensing images.
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
Change history
01 January 2022
In the originally published version of chapter 9 the name of the author was spelled incorrectly. The author name has been corrected as “Jun Li”.
References
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: MixMatch: a holistic approach to semi-supervised learning. In: Proceedings Advances in Neural Information Processing Systems (NIPS), pp. 5049–5059 (2019)
Dai, X., Wu, X., Wang, B., Zhang, L.: Semisupervised scene classification for remote sensing images: a method based on convolutional neural networks and ensemble learning. IEEE Geosci. Remote Sens. Lett. 16(6), 869–873 (2019). https://doi.org/10.1109/LGRS.2018.2886534
Dede, M.A., Aptoula, E., Genc, Y.: Deep network ensembles for aerial scene classification. IEEE Geosci. Remote Sens. Lett. 16(5), 732–735 (2018). https://doi.org/10.1109/LGRS.2018.2880136
Dong, Y., Zhang, Q.: A combined deep learning model for the scene classification of high-resolution remote sensing image. IEEE Geosci. Remote Sens. Lett. 16(10), 1540–1544 (2019). https://doi.org/10.1109/LGRS.2019.2902675
Han, W., Feng, R., Wang, L., Cheng, Y.: A semi-supervised generative framework with deep learning features for high-resolution remote sensing image scene classification. ISPRS-J. Photogramm. Remote Sens. 145, 23–43 (2018). https://doi.org/10.1016/j.isprsjprs.2017.11.004
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings IEEE Conference (CVPR), pp. 770–778 (2016)
Li, J., Socher, R., Hoi, S.C.: DivideMix: learning with noisy labels as semi-supervised learning. In: Proceedings ICLR (2019)
Liu, S., Niles-Weed, J., Razavian, N., Fernandez-Granda, C.: Early-learning regularization prevents memorization of noisy labels. arXiv:2007.00151 (2020)
Liu, Y., Liu, Y., Ding, L.: Scene classification based on two-stage deep feature fusion. IEEE Geosci. Remote Sens. Lett. 15(2), 183–186 (2017). https://doi.org/10.1109/LGRS.2017.2779469
Oliver, A., Odena, A., Raffel, C.A., Cubuk, E.D., Goodfellow, I.: Realistic evaluation of deep semi-supervised learning algorithms. In: Proceedings Advances in Neural Information Processing Systems (NIPS), pp. 3235–3246 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings ICLR (2014)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings Advances in Neural Information Processing Systems (NIPS), pp. 1195–1204 (2017)
Verma, V., Lamb, A., Kannala, J., Bengio, Y., Lopez-Paz, D.: Interpolation consistency training for semi-supervised learning. In: Proceedings Conference (AAAI), pp. 3635–3641 (2019)
Wei, H., Feng, L., Chen, X., An, B.: Combating noisy labels by agreement: a joint training method with co-regularization. In: Proceedings IEEE Conference (CVPR), pp. 13726–13735 (2020)
Xia, G.S., et al.: AID: a benchmark data set for performance evaluation of aerial scene classification. IEEE Trans. Geosci. Remote Sensing 55(7), 3965–3981 (2017). https://doi.org/10.1109/TGRS.2017.2685945
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: Proceedings ICLR (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Tian, Y., Li, J., Zhang, L., Sun, J., Yin, G. (2021). Selected Sample Retraining Semi-supervised Learning Method for Aerial Scene Classification. In: Fang, L., Chen, Y., Zhai, G., Wang, J., Wang, R., Dong, W. (eds) Artificial Intelligence. CICAI 2021. Lecture Notes in Computer Science(), vol 13069. Springer, Cham. https://doi.org/10.1007/978-3-030-93046-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-93046-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93045-5
Online ISBN: 978-3-030-93046-2
eBook Packages: Computer ScienceComputer Science (R0)