Quaternion based neural network for hyperspectral image classification
Quaternion based neural network for hyperspectral image classification
复制标题
基于四元数的神经网络用于高光谱图像分类
DOI：
10.1117/12.2558808
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Agaian, Sos S.
中科院分区：
文献类型：
--
作者：
Rao, Shishir Paramathma;Panetta, Karen;Agaian, Sos S.
神经网络已经成为解决高光谱图像（HIS）分类问题的最合适的方法。卷积神经网络（CNN）是目前各种分类任务的最新技术，在HSI的背景下有一些局限性。这些CNN模型非常容易过拟合，因为1）缺乏可用的训练样本，2）大量的参数需要微调。此外，CNN使用的学习率必须很小，以避免梯度消失，因此梯度下降需要很小的步骤来收敛并减慢模型运行时间。为了克服这些缺点，本文提出了一种新的基于四元数的高光谱图像分类网络（QHIC网）。QHIC Net可以对单个像素的光谱通道之间的局部依赖性和描述由一组像素形成的边缘或形状的全局结构关系进行建模，使其适用于小型和多样化的HSI数据集。在三个HSI数据集上的实验结果表明，Q-HIC Net与传统的基于CNN的HSI分类方法相比，参数数量少得多。
Neural networks have emerged to be the most appropriate method for tackling the classification problem for hyperspectral images (HIS). Convolutional neural networks (CNNs), being the current state-of-art for various classification tasks, have some limitations in the context of HSI. These CNN models are very susceptible to overfitting because of 1) lack of availability of training samples, 2) large number of parameters to fine-tune. Furthermore, the learning rates used by CNN must be small to avoid vanishing gradients, and thus the gradient descent takes small steps to converge and slows down the model runtime. To overcome these drawbacks, a novel quaternion based hyperspectral image classification network (QHIC Net) is proposed in this paper. The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels, making it suitable for HSI datasets that are small and diverse. Experimental results on three HSI datasets demonstrate that the Q-HIC Net performs on par with the traditional CNN based methods for HSI Classification with a far fewer number of parameters.