Skip to main content
SpringerLink
Log in

Consistency regularization teacher–student semi-supervised learning method for target recognition in SAR images

  • Original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Synthetic aperture radar automatic target recognition (SAR-ATR) is a hotspot in the field of remote sensing, which has been widely used in disaster monitoring, environmental monitoring, resource exploration, and crop yield estimates. In recent years, deep convolutional neural networks (DCNNs) have achieved promising performance among a variety of supervised classification methods under the condition of sufficiently labeled samples. However, it is expensive and time-consuming to collect large amounts of labeled samples suitable for DCNNs in SAR domains. To reduce the dependence of SAR-ATR on labeled samples, in this work, a consistency regularization teacher–student semi-supervised (CRTS) method for SAR-ATR is proposed, in which consistency regularization is applied to analyze and divide unlabeled samples and the teacher–student structure is introduced to generate pseudo-labels for the divided unlabeled samples. Firstly, by using consistent pseudo-label prediction, unlabeled samples are divided into consistent unlabeled samples and confident unlabeled samples. Then, in order to improve the quality of pseudo-labeled labels, the student model is used to generate a pseudo-label for consistent unlabeled samples, and the teacher model which is ensembled by the other two student models labels the confident unlabeled samples. Finally, these pseudo-label unlabeled samples are mixed with the labeled samples and trained together to improve recognition performance. Experiments are conducted on the MSTAR dataset, and the results demonstrate the effectiveness of the proposed method. As compared with several state-of-the-art methods, the recognition accuracy shows the superiority of the proposed method, especially when the training dataset is limited.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. El-Darymli, K., McGuire, P., Power, D., Moloney, C.R.: Target detection in synthetic aperture radar imagery: A state-of-the-art survey. J. Appl. Remote Sens. 7(1), 071598 (2013). https://doi.org/10.1117/1.JRS.7.071598

    Article  Google Scholar 

  2. Lang, H., Wu, S., Xu, Y.: Ship classification in SAR images improved by AIS knowledge transfer. IEEE Geosci. Remote Sens. Lett. 15(3), 439–443 (2018). https://doi.org/10.1109/LGRS.2018.2792683

    Article  Google Scholar 

  3. Han, D., Du, Q., Aanstoos, J.V., Younan, N.: Classification of levee slides from airborne synthetic aperture radar images with efficient spatial feature extraction. J. Appl. Remote Sens. 9(1), 097294 (2015). https://doi.org/10.1117/1.JRS.9.097294

    Article  Google Scholar 

  4. Guo, D., Chen, B.: In: SAR image target recognition via deep bayesian generative network, pp. 1–4. IEEE (2017)

  5. Zhang, J., Song, H., Zhou, B.: SAR target classification based on deep forest model. Remote Sens. 12(1), 128 (2020). https://doi.org/10.3390/rs12010128

    Article  Google Scholar 

  6. Lan, R., Sun, H.: Automated human motion segmentation via motion regularities. Vis. Comput. 31(1), 35–53 (2015). https://doi.org/10.1007/s00371-017-1411-8

    Article  Google Scholar 

  7. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. Presented at the (2018)

  8. Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. Presented at the (2020). https://doi.org/10.1109/CVPR42600.2020.01070

  9. Chen, L., Wang, R., Yang, J., Xue, L., Hu, M.: Multi-label image classification with recurrently learning semantic dependencies. Vis. Comput. 35(10), 1361–1371 (2019)

    Article  Google Scholar 

  10. Huang, K., Gao, S.: Image saliency detection via multi-scale iterative CNN. The Visual Computer pp. 1–13 (2019). https://doi.org/10.1007/s00371-019-01734-2

  11. Donahue, J., Simonyan, K.: Large scale adversarial representation learning. In: Advances in Neural Information Processing Systems, pp. 10542–10552 (2019)

  12. Zhang, J., Wang, C., Li, C., Qin, H.: Example-based rapid generation of vegetation on terrain via CNN-based distribution learning. Vis. Comput. 35(6–8), 1181–1191 (2019). https://doi.org/10.1007/s00371-019-01667-w

    Article  Google Scholar 

  13. Wu, Y., Yuan, Y., Guan, J., Yin, L., Chen, J., Zhang, G., Feng, P.: Joint convolutional neural network for small-scale ship classification in SAR Images. Presented at the (2019). https://doi.org/10.1109/IGARSS.2019.8897831

  14. Tian, Z., Wang, L., Zhan, R., Hu, J., Zhang, J.: Classification via weighted kernel CNN: Application to SAR target recognition. Int. J. Remote Sens. 39(23), 9249–9268 (2018). https://doi.org/10.1080/01431161.2018.1531317

    Article  Google Scholar 

  15. Wagner, S.: Morphological component analysis in SAR images to improve the generalization of ATR systems. In: International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa), pp. 46–50 (2015). https://doi.org/10.1109/CoSeRa.2015.7330261

  16. Gao, F., Yang, Y., Wang, J., Sun, J., Yang, E., Zhou, H.: A Deep Convolutional Generative Adversarial Networks (DCGANs)-based semi-supervised method for object recognition in Synthetic Aperture Radar (SAR) images. Remote Sens. 10(6), 846 (2018). https://doi.org/10.3390/rs10060846

    Article  Google Scholar 

  17. Gao, F., Shi, W., Wang, J., Hussain, A., Zhou, H.: A semi-supervised synthetic aperture radar (SAR) image recognition algorithm based on an attention mechanism and bias-variance decomposition. IEEE Access 7, 108617–108632 (2019). https://doi.org/10.1109/ACCESS.2019.2933459

    Article  Google Scholar 

  18. Qiao, S., Shen, W., Zhang, Z., Wang, B., Yuille, A.: Deep co-training for semi-supervised image recognition. Presented at the (2018)

  19. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: A holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, pp. 5049–5059 (2019)

  20. Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv:1610.02242 (2016)

  21. Miyato, T., Maeda, S.i., Koyama, M., Ishii, S. : Virtual adversarial training: A regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Analy. Machine Intell. 41(8), 1979–1993 (2019). https://doi.org/10.1109/TPAMI.2018.2858821

  22. Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, pp. 1195–1204 (2017)

  23. Ke, Z., Wang, D., Yan, Q., Ren, J., Lau, R.W.: Dual student: Breaking the limits of the teacher in semi-supervised learning. Presented at the (2019). https://doi.org/10.1109/ICCV.2019.00683

  24. Berthelot, D., Carlini, N., Cubuk, E.D., Kurakin, A., Sohn, K., Zhang, H., Raffel, C.: Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785 (2019)

  25. Sohn, K., Berthelot, D., Li, C.L., Zhang, Z., Carlini, N., Cubuk, E.D., Kurakin, A., Zhang, H., Raffel, C.: Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685 (2020)

  26. Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. arXiv:1904.12848 (2019)

  27. Verma, V., Lamb, A., Kannala, J., Bengio, Y., Lopez-Paz, D.: In: Interpolation consistency training for semi-supervised learning, pp. 3635–3641. AAAI Press (2019)

  28. Nair, V., Alonso, J.F., Beltramelli, T.: Realmix: Towards realistic semi-supervised deep learning algorithms. arXiv:1912.08766 (2019)

  29. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: Beyond empirical risk minimization. Presented at the (2018)

  30. Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Advances in Neural Information Processing Systems, pp. 529–536 (2005)

  31. Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv:1605.07146 (2016)

Download references

Funding

Our research fund is funded by Natural Science Foundation of Heilongjiang Province No.F2018006, China Postdoctoral Science Foundation No. 2019M661319, Fundamental Research Fund for the Central Universities (3072021CF0609).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China

    Ye Tian, Liguo Zhang, Jianguo Sun, Guisheng Yin & Yuxin Dong

Authors
  1. Ye Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Liguo Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianguo Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guisheng Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuxin Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuxin Dong.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, Y., Zhang, L., Sun, J. et al. Consistency regularization teacher–student semi-supervised learning method for target recognition in SAR images. Vis Comput 38, 4179–4192 (2022). https://doi.org/10.1007/s00371-021-02287-z

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-021-02287-z

Keywords

Search

Navigation