IEEE Trans Cybern. 2022 May;52(5):2981-2993. doi: 10.1109/TCYB.2020.3020540. Epub 2022 May 19.
Recently, deep-learning-based feature extraction (FE) methods have shown great potential in hyperspectral image (HSI) processing. Unfortunately, it also brings a challenge that the training of the deep learning networks always requires large amounts of labeled samples, which is hardly available for HSI data. To address this issue, in this article, a novel unsupervised deep-learning-based FE method is proposed, which is trained in an end-to-end style. The proposed framework consists of an encoder subnetwork and a decoder subnetwork. The structure of the two subnetworks is symmetric for obtaining better downsampling and upsampling representation. Considering both spectral and spatial information, 3-D all convolution nets and deconvolution nets are used to structure the encoder subnetwork and decoder subnetwork, respectively. However, 3-D convolution and deconvolution kernels bring more parameters, which can deteriorate the quality of the obtained features. To alleviate this problem, a novel cost function with a sparse regular term is designed to obtain more robust feature representation. Experimental results on publicly available datasets indicate that the proposed method can obtain robust and effective features for subsequent classification tasks.
最近，基于深度学习的特征提取 (FE) 方法在高光谱图像 (HSI) 处理中显示出巨大的潜力。不幸的是，这也带来了一个挑战，即深度学习网络的训练总是需要大量的标记样本，而这对于 HSI 数据来说几乎是不可能的。为了解决这个问题，本文提出了一种新颖的基于无监督深度学习的 FE 方法，该方法采用端到端的方式进行训练。所提出的框架由一个编码器子网和一个解码器子网组成。两个子网的结构是对称的，以获得更好的下采样和上采样表示。考虑到光谱和空间信息，分别使用 3-D 全卷积网络和反卷积网络来构建编码器子网和解码器子网。然而，3-D 卷积和反卷积核带来了更多的参数，这可能会降低所获得特征的质量。为了解决这个问题，设计了一种具有稀疏正则项的新代价函数，以获得更稳健的特征表示。在公开数据集上的实验结果表明，所提出的方法可以为后续的分类任务获得稳健有效的特征。
