期刊
PATTERN RECOGNITION
卷 132, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2022.108969
关键词
Hyperspectral data; Unsupervised band selection; Autoencoder; Stochastic gate
资金
- National Natural Science Foundation of China [61922014]
Due to its strong feature representation ability, the deep learning-based method is preferred for the unsupervised band selection task of hyperspectral image. However, the current methods have not investigated the nonlinear relationship between spectral bands, calling for a more robust model and effective loss function. In this paper, a novel stochastic gate-based autoencoder is proposed, which directly obtains the desired band subset with learnable parameters. The inclusion of a nonlinear regularization term and an early stopping criteria further improve the performance of the method.
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.(c) 2022 Published by Elsevier Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据