Convolutional neural networks (CNNs) have been applied for hyperspectral image classification recently. Among this class of deep models, 3-D CNN has been shown to be more effective by learning discriminative features from abundant spectral signatures and spatial contexts in hyperspectral imagery (HSI). However, by simply imposing 3-D CNN to HSI, a large amount of initial information might be lost in this CNN pipeline. The proposed attention-aware pseudo-3-D (AP3D) convolutional network for HSI classification is motivated by two observations. First, each dimension of the 3-D HSI is not equally important, different attention should be paid to different dimensions of the initial HSI image, especially in the first convolution operation. Second, intermediate representations of the 3-D input image at different stages in the 3-D CNN pipeline represent different levels of features and should not be neglected and abandoned. Instead, a 2-D matrix of scores for each feature map should be fed to the final softmax layer. Quantitative and qualitative results demonstrate that the proposed AP3D model outperforms the state-of-the-art HSI classification methods in agricultural and rural/urban data sets: Indian Pines, Pavia University, and Salinas Scene.

中文翻译：

---

用于高光谱图像分类的注意力感知伪 3-D 卷积神经网络

卷积神经网络（CNN）最近已应用于高光谱图像分类。在此类深度模型中，3-D CNN 已被证明通过从高光谱图像 (HSI) 中丰富的光谱特征和空间上下文中学习判别特征更有效。然而，通过简单地将 3-D CNN 强加给 HSI，在这个 CNN 管道中可能会丢失大量初始信息。提出的用于 HSI 分类的注意力感知伪 3-D (AP3D) 卷积网络是由两个观察结果激发的。首先，3-D HSI的每个维度并不是同等重要的，对初始HSI图像的不同维度应该给予不同的关注，尤其是在第一次卷积运算中。第二，3-D CNN 管道中不同阶段的 3-D 输入图像的中间表示代表不同级别的特征，不应被忽视和放弃。相反，每个特征图的二维分数矩阵应该被馈送到最终的 softmax 层。定量和定性结果表明，所提出的 AP3D 模型优于农业和农村/城市数据集中最先进的 HSI 分类方法：印度松树、帕维亚大学和萨利纳斯场景。