Hyperspectral Image Classification Using Random Occlusion Data Augmentation
Hyperspectral Image Classification Using Random Occlusion Data Augmentation
复制标题
DOI：
10.1109/lgrs.2019.2909495
复制
发表时间：
2019-11-01
影响因子：
4.8
通讯作者：
Li, Jun
中科院分区：
文献类型：
--
作者：
Haut, Juan Mario;Paoletti, Mercedes E.;Li, Jun
卷积神经网络（CNN）由于其强大的泛化能力和高精度，已成为遥感高光谱图像（HSI）分类的有力工具。然而，由于大量的参数，需要学习和HSI数据本身的复杂性，这些方法必须处理过拟合的重要问题，这可能会导致泛化不足和精度损失。为了缓解这个问题，在这封信中，我们采用随机遮挡，这是最近开发的一种用于训练CNN的数据增强（DA）方法，其中HSI中不同矩形空间区域的像素被随机遮挡，生成具有各种遮挡程度的训练图像，并降低过拟合的风险。我们的结果与两个著名的HSIs显示，所提出的方法有助于实现更好的分类精度与低的计算成本。
Convolutional neural networks (CNNs) have become a powerful tool for remotely sensed hyperspectral image (HSI) classification due to their great generalization ability and high accuracy. However, owing to the huge amount of parameters that need to be learned and to the complex nature of HSI data itself, these approaches must deal with the important problem of overfitting, which can lead to inadequate generalization and loss of accuracy. In order to mitigate this problem, in this letter, we adopt random occlusion, a recently developed data augmentation (DA) method for training CNNs, in which the pixels of different rectangular spatial regions in the HSI are randomly occluded, generating training images with various levels of occlusion and reducing the risk of overfitting. Our results with two well-known HSIs reveal that the proposed method helps to achieve better classification accuracy with low computational cost.