uDAS: An Untied Denoising Autoencoder With Sparsity for Spectral Unmixing
uDAS: An Untied Denoising Autoencoder With Sparsity for Spectral Unmixing
复制标题
DOI：
10.1109/tgrs.2018.2868690
复制
发表时间：
2019-03
影响因子：
8.2
通讯作者：
Ying Qu;H. Qi
中科院分区：
文献类型：
--
作者：
Ying Qu;H. Qi
线性光谱解混是将混合像元分解成组成端元和估计丰度的线性组合。本文主要研究了端元先验未知的无监督光谱解混。传统的方法使用基于几何或统计的方法。在本文中，我们使用无监督深度学习模型解决了光谱解混的挑战，特别是自编码器模型，其中解码器作为端元，隐藏层输出作为丰度。在最近的几次尝试中，基于部分的自编码器被设计用来解决无监督的光谱解混问题。然而，表现并不令人满意。在本文中，我们首先讨论了我们在基于零件的自动编码器问题上的一些重要发现。通过反例证明，通过对网络结构做出这些不适当的假设，我们表明所有现有的具有非负和捆绑编码器和解码器的基于零件的自编码器网络都存在固有缺陷。因此，它们不适合解决光谱解混问题。提出了一种具有稀疏性的非联合去噪自编码器，其中网络的编码器和解码器是独立的，只有网络的解码器被强制为非负的。此外，我们对网络设计做了两个关键的补充。首先，由于去噪是光谱解混的必要步骤，我们建议将去噪能力以去噪约束的形式纳入网络优化，而不是层叠另一个去噪预处理程序，以避免引入额外的重构误差。其次，为了增强对端元数量估计不准确的鲁棒性，我们在网络编码器上采用了$l_{21}$ -范数来减少冗余端元，同时降低重构误差。实验结果表明，该方法优于几种最先进的方法，特别是对于高噪声数据。
Linear spectral unmixing is the practice of decomposing the mixed pixel into a linear combination of the constituent endmembers and the estimated abundances. This paper focuses on unsupervised spectral unmixing where the endmembers are unknown a priori. Conventional approaches use either geometrical- or statistical-based approaches. In this paper, we address the challenges of spectral unmixing with unsupervised deep learning models, in specific, the autoencoder models, where the decoder serves as the endmembers and the hidden layer output serves as the abundances. In several recent attempts, part-based autoencoders have been designed to solve the unsupervised spectral unmixing problem. However, the performance has not been satisfactory. In this paper, we first discuss some important findings we make on issues with part-based autoencoders. By proof of counterexample, we show that all existing part-based autoencoder networks with nonnegative and tied encoder and decoder are inherently defective by making these inappropriate assumptions on the network structure. As a result, they are not suitable for solving the spectral unmixing problem. We propose a so-called untied denoising autoencoder with sparsity, in which the encoder and decoder of the network are independent, and only the decoder of the network is enforced to be nonnegative. Furthermore, we make two critical additions to the network design. First, since denoising is an essential step for spectral unmixing, we propose to incorporate the denoising capacity into the network optimization in the format of a denoising constraint rather than cascading another denoising preprocessor in order to avoid the introduction of additional reconstruction error. Second, to be more robust to the inaccurate estimation of a number of endmembers, we adopt an $l_{21}$ -norm on the encoder of the network to reduce the redundant endmembers while decreasing the reconstruction error simultaneously. The experimental results demonstrate that the proposed approach outperforms several state-of-the-art methods, especially for highly noisy data.