Stochastic gate-based autoencoder for unsupervised hyperspectral band selection. (December 2022)

• Record Type: Journal Article
• Authors: Sun, He; Zhang, Lei; Wang, Lizhi; Huang, Hua
• Is Part Of: Pattern recognition. Volume 132(2022)
• Publication Date: 2022-12
• Subjects: Hyperspectral data -- Unsupervised band selection -- Autoencoder -- Stochastic gate; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108969
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel unsupervised band selection method based on a stochastic gate-based autoencoder. A novel regularization term for further investigating the nonlinear relationship between spectral bands. An early stopping criterion for avoiding the overfitting of the proposed network. Abstract: Due to its strong feature representation ability, the deep learning (DL)-based method is preferable for the unsupervised band selection task of hyperspectral image (HSI). However, the current DL-based UBS methods have not further investigated the nonlinear relationship between spectral bands, a more robust DL model with effective loss function is desired. To solve the above problem, a novel stochastic gate-based autoencoder (SGAE) has been proposed for the UBS task. With the proposed stochastic gate layer, the desired band subset with learnable parameters can be directly obtained. For obtaining better UBS results, a nonlinear regularization term is added with the loss function to supervise the training process of SGAE. Furthermore, an early stopping criteria with a regularization term-based threshold is developed. Experimental results on four publicly available remote sensing datasets prove the effectiveness of our SGAE.