SEMI-SUPERVISED PolSAR IMAGE CLASSIFICATION BASED ON CROSSPSEUDO SUPERVISION AND HYBRID CONVOLUTIONAL NEURAL NETWORK

Fanfeng Shi and Fang Zheng

References

  1. [1] M.M. Sylaja and J. Kurian, Robot task recognition using deepconvolutional long short-term memory, Mechatronic Systemsand Control, 51(2), 2023, 106–113.
  2. [2] M. Li and Y. Wang, Vision-based carpet similarity inspectionusing deep learning and genetic algorithms, MechatronicSystems and Control, 49(3), 2021, 157.
  3. [3] Z. Yaghoubi and H.A. Talebi, Robust cluster consensus ofgeneral fractional-order nonlinear multi-agent systems withdynamic uncertainty, Mechatronic Systems and Control, 48(3),2020 165-170.
  4. [4] W. Wang, J. Wang, D. Quan, M. Yang, J. Sun, and B. Lu,PolSAR image classification via a multi-granularity hybridCNN-VIT model with external tokens and cross-attention,IEEE Journal of Selected Topics in Applied Earth Observationsand Remote Sensing, 17, 2024, 8003–8019.
  5. [5] Q. Zhang, X. Fang, T. Liu, R. Wu, L. Liu, and C. He,MCDiff: A multi-level conditional diffusion model for PolSARimage classification, IEEE Journal of Selected Topics inApplied Earth Observations and Remote Sensing, 18, 2025,6721–6737.
  6. [6] W. Hua, S. Wang, H. Liu, K. Liu, Y. Guo, and L. Jiao,Semisupervised PolSAR image classification based on improvedcotraining, IEEE Journal of Selected Topics in Applied EarthObservations and Remote Sensing, 10(11), 2017, 4971–4986.
  7. [7] J. Guo, L. Wang, D. Zhu, and G. Zhang, Semisupervisedclassification of PolSAR images using a novel memoryconvolutional neural network, IEEE Geoscience and RemoteSensing Letters, 19, 2021, 1–5.
  8. [8] X. Li, J. Yu, and L. Han, Semi-supervised classificationmethod for PolSAR based on vision transformer (ViT), inProceedings of Fourth International Conference on SignalImage Processing and Communication (ICSIPC 2024), 2024,138–149.
  9. [9] M. Li, Q. Li, and Y. Wang, Class balanced adaptive pseudolabeling for federated semi-supervised learning, in Proceedingsof the IEEE/CVF Conference on Computer Vision and PatternRecognition, 2023, 16292–16301.
  10. [10] R. Tang, F. Pu, R. Yang, Z. Xu, and X. Xu, Multi-domain fusiongraph network for semi-supervised PolSAR image classification,Remote Sensing, 15(1), 2022, 160.
  11. [11] W. Xie, G. Ma, F. Zhao, H. Liu, and L. Zhang, PolSAR imageclassification via a novel semi-supervised recurrent complex-valued convolution neural network, Neurocomputing, 388, 2020,255–268.
  12. [12] X. Chen, Y. Yuan, G. Zeng, and J. Wang, Semi-supervisedsemantic segmentation with cross pseudo supervision, in77Proceedings of the IEEE/CVF Conference on Computer Visionand Pattern Recognition, 2021, 2613–2622.
  13. [13] J. Zou and H. Zhang, New key point detection technologyunder real-time eye tracking, Mechatronic Systems and Control,47(2), 2019, 71–76.
  14. [14] Z. Zhang, H. Wang, F. Xu, and Y.Q. Jin, Complex-valuedconvolutional neural network and its application in polarimetricSAR image classification, IEEE Transactions on Geoscienceand Remote Sensing, 55(12), 2017, 7177–7188.
  15. [15] X. Tan, M. Li, P. Zhang, Y. Wu, and W. Song, Complex-valued 3-D convolutional neural network for PolSAR imageclassification, IEEE Geoscience and Remote Sensing Letters,17(6), 2019, 1022–1026.
  16. [16] X. Yang, Z. Song, I. King, and Z. Xu, A survey on deepsemi-supervised learning, IEEE Transactions on Knowledgeand Data Engineering, 35(9), 2022, 8934–8954.
  17. [17] S. Zhou, S. Tian, L. Yu, W. Wu, D. Zhang, Z. Peng,Z. Zhou, and J. Wang, FixMatch-LS: Semi-supervised skinlesion classification with label smoothing, Biomedical SignalProcessing and Control, 84, 2023, 104709.
  18. [18] Z. Jiang, Y. Zhan, Q. Mao, and Y. Du, Semi-supervisedclustering under a “compact-cluster” assumption, IEEETransactions on Knowledge and Data Engineering, 35(5), 2022,5244–5256.
  19. [19] S. Zhang, K. Huang, J. Zhu, and Y. Liu, Manifold adversarialtraining for supervised and semi-supervised learning, NeuralNetworks, 140, 2021, 282–293.
  20. [20] A. Abuduweili, X. Li, H. Shi, C.Z. Xu, and D. Dou, Adaptiveconsistency regularization for semi-supervised transfer learning,in Proceedings of the IEEE/CVF conference on computer visionand pattern recognition, 2021, 6923–6932.
  21. [21] K.C. Huarng and C.C. Yeh, A unitary transformation methodfor angle-of-arrival estimation, IEEE Transactions on SignalProcessing, 39(4), 1991, 975–977.
  22. [22] J. Geng, X. Ma, J. Fan, and H. Wang, Semisupervisedclassification of polarimetric SAR image via superpixelrestrained deep neural network, IEEE Geoscience and RemoteSensing Letters, 15(1), 2017, 122–126.
  23. [23] H. Liu, R. Luo, F. Shang, X. Meng, S. Gou, and B. Hou, Semi-supervised deep metric learning networks for classification ofpolarimetric SAR data, Remote Sensing, 12(10), 2020, 1593.
  24. [24] Y. Li, R. Xing, L. Jiao, Y. Chen, Y. Chai, N. Marturi, and R.Shang, Semi-supervised PolSAR image classification based onself-training and superpixels, Remote Sensing, 11(16), 2019,1933.
  25. [25] W. Hua, Y. Zhang, H. Liu, W. Xie, and X. Jin, Multichannelsemi-supervised active learning for PolSAR image classification,International Journal of Applied Earth Observation andGeoinformation, 127, 2024, 103706.
  26. [26] W. Li, H. Xia, B. Xi, Y. Wang, J. Lu, and Y. He, SSL-MBC:Self-supervised learning with multi-branch consistency for few-shot PolSAR image classification, IEEE Journal of SelectedTopics in Applied Earth Observations and Remote Sensing,18, 2025, 4696–4710.

Important Links:

Go Back