Anterior|Siguiente

Class-independent domain adaptation for hyperspectral image classification

  • role： First author第一作者
  • Affiliation：

    School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China

  • Email：yulong6@mail2.sysu.edu.cn
  • Introduction：余龙，研究方向为高光谱图像处理。E-mail： yulong6@mail2.sysu.edu.cn
YU Long1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Hubei Key Laboratory of Intelligent Geo-Information Processing, School of Computer Science, China University of Geosciences, Wuhan 430078, China

  • Email：lijuncug@cug.edu.cn
  • Introduction：李军，研究方向为高光谱图像分类、分割、混合像元分解。E-mail： lijuncug@cug.edu.cn
LI Jun2*,  
  • Affiliation：

    School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China

HE Lin3,  
  • Affiliation：

    School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, China

LI Yunfei1

resumen

Hyperspectral image supervised classification is a crucial and challenging task in remote sensing, as its performance depends heavily on the quantity and quality of labeled samples. However, labeling hyperspectral data is a difficult and time-consuming procedure. This problem results in a limited number of labeled samples in real-world scenarios, rendering the supervised classifiers vulnerable to the issue of overfitting. To address this problem, researchers have sought solutions in the field of unsupervised domain adaptation, utilizing labeled samples from previous images (source domain) to classify new hyperspectral data (target domain). Most existing domain adaptation methods strive to learn domain-invariant features in a new space, but many of them focus on aligning the overall statistics of the two domains without considering the spectral shifts in each class. Other methods attempt to align every class of the source and target domains simultaneously but often overlook the issues of mixture of samples across classes and incorrect sample selection. This may lead to a negative transfer and reduced separability of data. The significant discrepancies across domains will further compound the problem.In this paper, we propose a novel class-independent domain adaptation algorithm that addresses these issues in hyperspectral image classification. Our method first creates an independent subspace for each class and then aligns the corresponding single-class samples of the two domains in those subspaces. The posterior probabilities are learned independently through the aligned samples in each subspace. Then, the posterior probabilities obtained from multiple subspaces are fused to produce the final classification labels, aiming at increasing the confidence of results. Additionally, we use smoothed classification labels as pseudo labels for further iteration and incorporate a strategy for selecting representative samples to enhance subspace performance.Experimental results on two real hyperspectral datasets demonstrate the high classification performance of our proposed method. Compared to the joint domain adaptation algorithm, our method with the nearest neighbor classifier improved the accuracy by 9.56% on the Honghu data and 18.45% on the Wen-County data. Compared to other competitors, our method also has the advantage of generating smoother classification maps with more distinct boundaries of ground objects. These remarkable results stem from the substantial improvement in data separability achieved by our approach, which has been validated through calculations in our experiments.In conclusion, our proposed class-independent domain adaptation algorithm is a promising solution for hyperspectral image classification, providing high performance with reduced risk of overfitting. By aligning samples in the class-independent subspaces and fusing posterior probabilities, our method leads to improved data separability and more accurate classifications. Furthermore, the use of representative sample selection helps mitigate the potential impact of mislabeled samples on class alignments. Thus, our algorithm is able to overcome the limitations of existing domain adaptation methods and achieve improved results. In future work, we plan to extend our method to more complex high-dimensional datasets and incorporate advanced deep learning models. We also intend to evaluate the applicability of our method for real-time hyperspectral image classification, which is a critical requirement for many remote sensing applications. Overall, our research represents a significant advancement in the field of hyperspectral image classification, offering a new approach for solving the challenge of insufficient labeled samples.

palabra clave

remote sensing;hyperspectral image;domain adaptation;classification;class-independent subspace;ZY1-02D;GF-5

References

  1. 1.
    Anowar F, Sadaoui S and Selim B. 2021. Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE). Computer Science Review, 40: 100378
  2. 2.
    Belkin M, Niyogi P and Sindhwani V. 2006. Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. The Journal of Machine Learning Research, 7: 2399-2434
  3. 3.
    Boykov Y, Veksler O and Zabih R. 2001. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11): 1222-1239
  4. 4.
    Deng B, Jia S and Shi D M. 2020. Deep metric learning-based feature embedding for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 58(2): 1422-1435
  5. 5.
    Deng W X, Liao Q, Zhao L J, Guo D K, Kuang G Y, Hu D W and Liu L. 2021. Joint clustering and discriminative feature alignment for unsupervised domain adaptation. IEEE Transactions on Image Processing, 30: 7842-7855
  6. 6.
    Du B, Zhang L P, Tao D C and Zhang D Y. 2013. Unsupervised transfer learning for target detection from hyperspectral images. Neurocomputing, 120: 72-82
  7. 7.
    Fang Z Q, Yang Y X, Li Z K, Li W, Chen Y S, Ma L and Du Q. 2022. Confident learning-based domain adaptation for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5527116
  8. 8.
    Fernando B, Habrard A, Sebban M and Tuytelaars T. 2013. Unsupervised visual domain adaptation using subspace alignment//Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney: IEEE: 2960-2967
  9. 9.
    Gretton A, Borgwardt K M, Rasch M, Schölkopf B and Smola A J. 2007. A kernel method for the two-sample-problem//Advances in Neural Information Processing Systems 19. Vancouver: MIT: 513-520
  10. 10.
    Hardoon D R, Szedmak S and Shawe-Taylor J. 2004. Canonical correlation analysis: an overview with application to learning methods. Neural Computation, 16(12): 2639-2664
  11. 11.
    Hotelling H. 1936. Relations between two sets of variates. Biometrika, 28(3/4): 321-377
  12. 12.
    Huang M and Yin J H. 2022. Research on adversarial domain adaptation method and its application in power load forecasting. Mathematics, 10(18): 3223
  13. 13.
    Li J, Bioucas-Dias J M and Plaza A. 2012. Spectral–spatial hyperspectral image segmentation using subspace multinomial logistic regression and markov random fields. IEEE Transactions on Geoscience and Remote Sensing, 50(3): 809-823
  14. 14.
    Li M Y, Li S L, Zhao M, Fang Z Y, Zhang Y F and Yu Z T. 2022. Unsupervised domain adaptation insulator detection based on adversarial consistency constraints. Journal of Image and Graphics, 27(4): 1148-1160
  15. 15.
    Li X, Zhang L P, Du B and Zhang L F. 2019. On gleaning knowledge from cross domains by sparse subspace correlation analysis for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 57(6): 3204-3220
  16. 16.
    Li Y and Song P H. 2022. Review of transfer learning in medical image classification. Journal of Image and Graphics, 27(3): 672-686
  17. 17.
    Long M S, Wang J M, Ding G G, Sun J G and Yu P S. 2013. Transfer feature learning with joint distribution adaptation//Proceedings of the 2013 IEEE International Conference on Computer Vision. Sydney: IEEE: 2200-2207
  18. 18.
    Luo C and Ma L. 2018. Manifold regularized distribution adaptation for classification of remote sensing images. IEEE Access, 6: 4697-4708
  19. 19.
    Ma L, Crawford M M, Zhu L and Liu Y. 2019. Centroid and covariance alignment-based domain adaptation for unsupervised classification of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 57(4): 2305-2323
  20. 20.
    Ning Y J, Peng J T, Sun L, Huang Y, Sun W W and Du Q. 2022. Adaptive local discriminant analysis and distribution matching for domain adaptation in hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 4797-4808
  21. 21.
    Pan S J, Tsang I W, Kwok J T and Yang Q. 2011. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 22(2): 199-210
  22. 22.
    Peng J T, Sun W W, Wei T H and Fan W Q. 2020. A modified correlation alignment algorithm for the domain adaptation of GF-5 hyperspectral image. Journal of Remote Sensing (Chinese), 24(4): 417-426
  23. 23.
    Persello C and Bruzzone L. 2014. Active and semisupervised learning for the classification of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 52(11): 6937-6956
  24. 24.
    Shu Y, Cao Z J, Long M S and Wang J M. 2019. Transferable curriculum for weakly-supervised domain adaptation//Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Honolulu: AAAI: 4951-4958
  25. 25.
    Sun B, Feng J and Saenko K. 2016. Return of frustratingly easy domain adaptation//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Phoenix: AAAI: 2058-2065
  26. 26.
    Tan K, Wang X and Du P J. 2019. Research progress of the remote sensing classification combining deep learning and semi-supervised learning. Journal of Image and Graphics, 24(11): 1823-1841
  27. 27.
    Tang H, Wang Y W and Jia K. 2022. Unsupervised domain adaptation via distilled discriminative clustering. Pattern Recognition, 127: 108638
  28. 28.
    Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
  29. 29.
    Tuia D, Persello C and Bruzzone L. 2016. Domain adaptation for the classification of remote sensing data: an overview of recent advances. IEEE Geoscience and Remote Sensing Magazine, 4(2): 41-57
  30. 30.
    Tuia D, Volpi M, Trolliet M and Camps-Valls G. 2014. Semisupervised manifold alignment of multimodal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 52(12): 7708-7720
  31. 31.
    Wang H Y, Cheng Y H, Chen C L P and Wang X S. 2021. Semisupervised classification of hyperspectral image based on graph convolutional broad network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 2995-3005
  32. 32.
    Weiss K, Khoshgoftaar T M and Wang D D. 2016. A survey of transfer learning. Journal of Big Data, 3(1): 9
  33. 33.
    Yadav C S, Pradhan M K, Gangadharan S M P, Chaudhary J K, Singh J, Khan A A, Haq M A, Alhussen A, Wechtaisong C, Imran H, Alzamil Z S and Pattanayak H S. 2022. Multi-class pixel certainty active learning model for classification of land cover classes using hyperspectral imagery. Electronics, 11(17): 2799
  34. 34.
    Yang H L and Crawford M M. 2016. Spectral and spatial proximity-based manifold alignment for multitemporal hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 54(1): 51-64
  35. 35.
    Ying X, Liu Z, Zhu J L, Jiang H, Zhang R X and Gao J. 2023. Meta-optimized multi-adversarial domain adaptation for thyroid ultra-sound image. Journal of Image and Graphics, 28(1): 234-247
  36. 36.
    Zandifar M, Rezaie S and Tahmoresnezhad J. 2022. Transferred local fisher discriminant analysis.
  37. 37.
    Zhang J, Li W Q and Ogunbona P. 2017. Joint geometrical and statistical alignment for visual domain adaptation//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE: 5150-5158
  38. 38.
    Zhang Y X, Li W, Zhang M M, Qu Y, Tao R and Qi H R. 2023. Topological structure and semantic information transfer network for cross-scene hyperspectral image classification. IEEE Transactions on Neural Networks and Learning Systems, 34(6): 2817-2830
  39. 39.
    Zhao J C, Li L S, Deng F, He H B and Chen J. 2022. Discriminant geometrical and statistical alignment with density peaks for domain adaptation. IEEE Transactions on Cybernetics, 52(2): 1193-1206
  40. 40.
    Zheng Z, Wang J F, Zou B, Gao Y H, Yang S Q and Wang Y Q. 2022. Initial assessment of burn severity using the transfer learning model. National Remote Sensing Bulletin, 26(10): 2001-2013
  41. 41.
    Zhu L and Ma L. 2016. Class centroid alignment based domain adaptation for classification of remote sensing images. Pattern Recognition Letters, 83: 124-132

Leer el texto completo

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website