Abstract
In hyperspectral image (HSI) analysis, high-dimensional data may contain noisy, irrelevant and redundant information. To mitigate the negative effect from these information, feature selection is one of the useful solutions. Unsupervised feature selection is a data preprocessing technique for dimensionality reduction, which selects a subset of informative features without using any label information. Different from the linear models, the autoencoder is formulated to nonlinearly select informative features. The adjacency matrix of HSI can be constructed to extract the underlying relationship between each data point, where the latent representation of original data can be obtained via matrix factorization. Besides, a new feature representation can be also learnt from the autoencoder. For a same data matrix, different feature representations should consistently share the potential information. Motivated by these, in this paper, we propose a latent representation learning based autoencoder feature selection (LRLAFS) model, where the latent representation learning is used to steer feature selection for the autoencoder. To solve the proposed model, we advance an alternative optimization algorithm. Experimental results on three HSI datasets confirm the effectiveness of the proposed model.
Similar content being viewed by others
References
Abid A, Balin MF, Zou J (2019) Concrete autoencoders for differentiable feature selection and reconstruction. In: International conference on machine learning, pp 444–453
Andrychowicz M, Denil M, Gomez S, Hoffman MW, Pfau D, Schaul T, Shillingford B, De Freitas N (2016) Learning to learn by gradient descent by gradient descent. In: Advances in neural information processing systems, pp 3981–3989
Ap S C, Lauly S, Larochelle H, Khapra M, Ravindran B, Raykar V C, Saha A (2014) An autoencoder approach to learning bilingual word representations. In: Advances in neural information processing systems, pp 1853–1861
Cai D, Zhang C, He X (2010) Unsupervised feature selection for multi-cluster data. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 333–342
Chandra B, Sharma RK (2015) Exploring autoencoders for unsupervised feature selection. In: International joint conference on neural networks, pp 1–6
Fauvel M, Dechesne C, Zullo A, Ferraty F (2015) Fast forward feature selection of hyperspectral images for classification with gaussian mixture models. IEEE J Sel Top Appl Earth Observ Remote Sens 8(6):2824–2831
Feng S, Duarte MF (2018) Graph regularized autoencoder-based unsupervised feature selection. In: Asilomar conference on signals, systems, and computers, pp 55–59
Feng J, Jiao L, Liu F, Sun T, Zhang X (2016) Unsupervised feature selection based on maximum information and minimum redundancy for hyperspectral images. Pattern Recognit 51:295–309
Gnouma M, Ladjailia A, Ejbali R, Zaied M (2019) Stacked sparse autoencoder and history of binary motion image for human activity recognition. Multimed Tools Appl 78(2):2157–2179
Gui J, Sun Z, Ji S, Tao D, Tan T (2016) Feature selection based on structured sparsity: a comprehensive study. IEEE Trans Neural Netw Learn Syst 28(7):149–1507
Han K, Wang Y, Zhang C, Li C, Xu C (2018) Autoencoder inspired unsupervised feature selection. In: IEEE international conference on acoustics, speech and signal processing, pp 2941–2945
He X, Cai D, Niyogi P (2006) Laplacian score for feature selection. In: Advances in neural information processing systems, pp 507–514
Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670
Jia W, Muhammad K, Wang SH, Zhang YD (2019) Five-category classification of pathological brain images based on deep stacked sparse autoencoder. Multimed Tools Appl 78(4):4045–4064
Jiang J, Ma J, Chen C, Wang Z, Cai Z, Wang L (2018) Superpca: a superpixelwise pca approach for unsupervised feature extraction of hyperspectral imagery. IEEE Trans Geosci Remote Sens 56(8):4581–4593
Li S, Qi H (2011) Sparse representation based band selection for hyperspectral images. In: IEEE international conference on image processing, pp 2693–2696
Li Z, Tang J (2015) Unsupervised feature selection via nonnegative spectral analysis and redundancy control. IEEE Trans Image Process 24(12):5343–5355
Li J, Hu X, Wu L, Liu H (2009) Robust unsupervised feature selection on networked data. In: SIAM international conference on data mining, pp 387–395
Li Z, Liu J, Yang Y, Zhou X, Lu H (2013) Clustering-guided sparse structural learning for unsupervised feature selection. IEEE Trans Knowl Data Eng 26(9):2138–2150
Lunga D, Prasad S, Crawford MM, Ersoy O (2014) Manifold-learning-based feature extraction for classification of hyperspectral data: a review of advances in manifold learning. IEEE Signal Process Mag 31(1):55–66
Maillo J, García S, Luengo J, Herrera F, Triguero I (2019) Fast and scalable approaches to accelerate the fuzzy k-nearest neighbors classifier for big data. IEEE Trans Fuzzy Syst 28(5):874–886
Mitra P, Murthy C, Pal SK (2002) Unsupervised feature selection using feature similarity. IEEE Trans Pattern Anal Mach Intell 24(3):301–312
Pal M, Foody GM (2010) Feature selection for classification of hyperspectral data by svm. IEEE Trans Geosci Remote Sens 48(5):2297–2307
Prasad S, Bruce LM (2008) Limitations of principal components analysis for hyperspectral target recognition. IEEE Geosci Remote Sens Lett 5 (4):625–629
Serpico SB, Bruzzone L (2001) A new search algorithm for feature selection in hyperspectral remote sensing images. IEEE Trans Geosci Remote Sens 39 (7):1360–1367
Shen L, Zhu Z, Jia S, Zhu J, Sun Y (2012) Discriminative gabor feature selection for hyperspectral image classification. IEEE Geosci Remote Sens Lett 10(1):29–33
Tang C, Bian M, Liu X, Li M, Zhou H, Wang P, Yin H (2019) Unsupervised feature selection via latent representation learning and manifold regularization. Neural Netw 117:163–178
Taşkın G, Kaya H, Bruzzone L (2017) Feature selection based on high dimensional model representation for hyperspectral images. IEEE Trans Image Process 26(6):2918–2928
Wan Y, Ma A, Zhong Y, Hu X, Zhang L (2020) Multiobjective hyperspectral feature selection based on discrete sine cosine algorithm. IEEE Trans Geosci Remote Sens 58(5):3601–3618
Wang S, Tang J, Liu H (2015) Embedded unsupervised feature selection. In: AAAI conference on artificial intelligence, pp 470–476
Wang S, Ding Z, Fu Y (2017) Feature selection guided auto-encoder. In: AAAI conference on artificial intelligence, pp 2725–2731
Yang Y, Shen H T, Nie F, Ji R, Zhou X (2011) Nonnegative spectral clustering with discriminative regularization. In: Twenty-fifth AAAI conference on artificial intelligence, pp 555–560
Yang X, Deng C, Zheng F, Yan J, Liu W (2019) Deep spectral clustering using dual autoencoder network. In: IEEE conference on computer vision and pattern recognition, pp 4066–4075
Zeng K, Yu J, Wang R, Li C, Tao D (2015) Coupled deep autoencoder for single image super-resolution. IEEE Trans Cybern 47(1):27–37
Zhang Y, Jiang X, Wang X, Cai Z (2019) Spectral-spatial hyperspectral image classification with superpixel pattern and extreme learning machine. Remote Sens 11(17):1–20
Zhang Y, Wu J, Cai Z, Du B, Philip S Y (2019) An unsupervised parameter learning model for rvfl neural network. Neural Netw 112:85–97
Zhang Y, Wu J, Cai Z, Yu P (2020) Multi-view multi-label learning with sparse feature selection for image annotation. IEEE Trans Multimed 1–14. https://doi.org/10.1109/TMM.2020.2966887
Zhou Y, Peng J, Chen CP (2015) Dimension reduction using spatial and spectral regularized local discriminant embedding for hyperspectral image classification. IEEE Trans Geosci Remote Sens 53(2):1082–1095
Zhu X, Li X, Zhang S, Ju C, Wu X (2016) Robust joint graph sparse coding for unsupervised spectral feature selection. IEEE Trans Neural Netw Learn Syst 28(6):1263–1275
Acknowledgments
This work is supported in part by the National Nature Science Foundation of China under Grant 61703355, the Natural Science Foundation of Hubei Province of China under Grant 2020CFB328, the Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, X., Wang, Z., Zhang, Y. et al. Latent representation learning based autoencoder for unsupervised feature selection in hyperspectral imagery. Multimed Tools Appl 81, 12061–12075 (2022). https://doi.org/10.1007/s11042-020-10474-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10474-8