Stochastic gate-based autoencoder for unsupervised hyperspectral band selection

作者：

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.

摘要

•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.

论文关键词：Hyperspectral data,Unsupervised band selection,Autoencoder,Stochastic gate

论文评审过程：Received 5 May 2022, Revised 13 June 2022, Accepted 9 August 2022, Available online 10 August 2022, Version of Record 14 August 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108969