Hyperspectral image (HSI) classification is a vital but difficult task due to its significant spectral variability and nonlinear structure. Nowadays, complex spatial–spectral networks have achieved remarkable successes in HSI classification, but limited by the large complexity and hardware demands. Spectral networks with simple architectures alleviate this problem to some degree; however, most of them have downgraded performance as a result of insufficient excavation of spectral diagonal information and channel correlations. To overcome these problems, this article proposes a fresh atrous convolution channel attention-aided dense convolutional neural network (ACADCN) for HSI classification, which enhances the exploitation of spectral feature representations and channel correlations to provide a better classification with limited samples. On the one hand, an effective 1-D dense block is constructed to deeply mine spectral discriminability by taking the advantages of hierarchical representations and establish a deep 1-D convolutional neural network (1D CNN), with the complementarity of different level features integrated. On the other hand, a singularly designed atrous convolution channel attention (ACA) module is used to learn multiscale cross-channel correlations to make up the locality of convolutions. The effectiveness of ACADCN is verified on two commonly used HSIs, with a mean overall accuracy (OA) of 94.09%, an average accuracy (AA) of 94.63%, and a kappa of 0.9254 achieved. The experimental results show its superiority to the other advanced deep spectral classifiers.

中文翻译：

---

基于空洞卷积通道注意力辅助密集卷积神经网络的高光谱图像分类

高光谱图像（HSI）分类因其显着的光谱变化和非线性结构而成为一项重要但艰巨的任务。如今，复杂的空间光谱网络在 HSI 分类方面取得了显着的成功，但受到复杂性和硬件需求的限制。具有简单架构的谱网络在一定程度上缓解了这个问题；然而，由于对频谱对角信息和通道相关性的挖掘不充分，大多数方法的性能下降。为了克服这些问题，本文提出了一种用于 HSI 分类的新的空洞卷积通道注意辅助密集卷积神经网络（ACADCN），它增强了对光谱特征表示和通道相关性的利用，以在有限的样本下提供更好的分类。一方面，利用层次表示的优势，构建有效的一维密集块来深度挖掘谱可辨别性，并建立深度一维卷积神经网络（1D CNN），并综合不同层次特征的互补性。另一方面，采用独特设计的空洞卷积通道注意（ACA）模块来学习多尺度跨通道相关性，以弥补卷积的局部性。 ACADCN的有效性在两个常用的HSI上得到了验证，平均总体准确率（OA）为94.09%，平均准确率（AA）为94.63%，kappa为0.9254。实验结果表明其优于其他先进的深度光谱分类器。