当前位置: X-MOL 学术ISPRS J. Photogramm. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
MugNet: Deep learning for hyperspectral image classification using limited samples
ISPRS Journal of Photogrammetry and Remote Sensing ( IF 12.7 ) Pub Date : 2017-11-20 , DOI: 10.1016/j.isprsjprs.2017.11.003
Bin Pan , Zhenwei Shi , Xia Xu

In recent years, deep learning based methods have attracted broad attention in the field of hyperspectral image classification. However, due to the massive parameters and the complex network structure, deep learning methods may not perform well when only few training samples are available. In this paper, we propose a small-scale data based method, multi-grained network (MugNet), to explore the application of deep learning approaches in hyperspectral image classification. MugNet could be considered as a simplified deep learning model which mainly targets at limited samples based hyperspectral image classification. Three novel strategies are proposed to construct MugNet. First, the spectral relationship among different bands, as well as the spatial correlation within neighboring pixels, are both utilized via a multi-grained scanning approach. The proposed multi-grained scanning strategy could not only extract the joint spectral-spatial information, but also combine different grains’ spectral and spatial relationship. Second, because there are abundant unlabeled pixels available in hyperspectral images, we take full advantage of these samples, and adopt a semi-supervised manner in the process of generating convolution kernels. At last, the MugNet is built upon the basis of a very simple network which does not include many hyperparameters for tuning. The performance of MugNet is evaluated on a popular and two challenging data sets, and comparison experiments with several state-of-the-art hyperspectral image classification methods are revealed.



中文翻译:

MugNet:使用有限样本对深度光谱图像进行深度学习

近年来,基于深度学习的方法在高光谱图像分类领域引起了广泛的关注。但是,由于庞大的参数和复杂的网络结构,当只有很少的训练样本可用时,深度学习方法可能无法很好地执行。在本文中,我们提出了一种基于小规模数据的方法,即多粒度网络(MugNet),以探索深度学习方法在高光谱图像分类中的应用。MugNet可被视为简化的深度学习模型,主要针对基于有限样本的高光谱图像分类。提出了三种新颖的策略来构建MugNet。首先,通过多粒度扫描方法来利用不同频带之间的光谱关系以及相邻像素内的空间相关性。提出的多粒度扫描策略不仅可以提取联合的光谱空间信息,而且可以结合不同晶粒的光谱和空间关系。其次,由于高光谱图像中有大量可用的未标记像素,因此我们充分利用了这些样本,并在生成卷积核的过程中采用了半监督方式。最后,MugNet是基于非常简单的网络构建的,该网络不包含许多用于调整的超参数。MugNet的性能在一个受欢迎的和两个具有挑战性的数据集上进行了评估,并揭示了几种最先进的高光谱图像分类方法的对比实验。而且还结合了不同谷物的光谱和空间关系。其次,由于高光谱图像中有大量可用的未标记像素,因此我们充分利用了这些样本,并在生成卷积核的过程中采用了半监督方式。最后,MugNet是基于非常简单的网络构建的,该网络不包含许多用于调整的超参数。MugNet的性能在一个受欢迎的和两个具有挑战性的数据集上进行了评估,并揭示了几种最先进的高光谱图像分类方法的对比实验。而且还结合了不同谷物的光谱和空间关系。其次,由于高光谱图像中有大量可用的未标记像素,因此我们充分利用了这些样本,并在生成卷积核的过程中采用了半监督方式。最后,MugNet是基于非常简单的网络构建的,该网络不包含许多用于调整的超参数。MugNet的性能在一个受欢迎的和两个具有挑战性的数据集上进行了评估,并揭示了几种最先进的高光谱图像分类方法的对比实验。MugNet是基于非常简单的网络构建的,该网络不包含许多用于调整的超参数。MugNet的性能在一个受欢迎的和两个具有挑战性的数据集上进行了评估,并揭示了几种最先进的高光谱图像分类方法的对比实验。MugNet是基于非常简单的网络构建的,该网络不包含许多用于调整的超参数。MugNet的性能在一个受欢迎的和两个具有挑战性的数据集上进行了评估,并揭示了几种最先进的高光谱图像分类方法的对比实验。

更新日期:2018-06-03
down
wechat
bug