论文标题
通过频谱不混合改善深度高光谱图像分类性能
Improving Deep Hyperspectral Image Classification Performance with Spectral Unmixing
论文作者
论文摘要
神经网络的最新进展在高光谱图像（HSI）分类方面取得了长足的进步。但是，主要是由复杂的模型结构和小型训练集引起的过度拟合效果仍然是一个主要问题。降低神经网络的复杂性可以在某种程度上防止过度拟合，但也降低了网络表达更抽象特征的能力。扩大训练集也很困难，因为收购和手动标签的高昂费用。在本文中，我们提出了一种基于丰富的多HSI分类方法。首先，我们通过数据集特定的自动编码器将每个HSI从光谱域转换为丰度域。其次，收集了来自多个HSI的丰度表示形式以形成扩大的数据集。最后，我们培训一个基于丰富的分类器，并使用分类器来预测所有相关的HSI数据集。与通常高度混合的光谱不同，丰度的特征在降低的尺寸中更具代表性，而噪声则更少。这使建议的方法采用简单的分类器和扩大培训数据，并期望过度拟合的问题更少。通过消融研究和比较实验验证了所提出方法的有效性。
Recent advances in neural networks have made great progress in the hyperspectral image (HSI) classification. However, the overfitting effect, which is mainly caused by complicated model structure and small training set, remains a major concern. Reducing the complexity of the neural networks could prevent overfitting to some extent, but also declines the networks' ability to express more abstract features. Enlarging the training set is also difficult, for the high expense of acquisition and manual labeling. In this paper, we propose an abundance-based multi-HSI classification method. Firstly, we convert every HSI from the spectral domain to the abundance domain by a dataset-specific autoencoder. Secondly, the abundance representations from multiple HSIs are collected to form an enlarged dataset. Lastly, we train an abundance-based classifier and employ the classifier to predict over all the involved HSI datasets. Different from the spectra that are usually highly mixed, the abundance features are more representative in reduced dimension with less noise. This benefits the proposed method to employ simple classifiers and enlarged training data, and to expect less overfitting issues. The effectiveness of the proposed method is verified by the ablation study and the comparative experiments.
