Zheng Xiangtao, Sun Hao, Lu Xiaoqiang, Xie Wei
IEEE Trans Image Process. 2022;31:4251-4265. doi: 10.1109/TIP.2022.3177322. Epub 2022 Jun 29.
Hyperspectral image (HSI) classification refers to identifying land-cover categories of pixels based on spectral signatures and spatial information of HSIs. In recent deep learning-based methods, to explore the spatial information of HSIs, the HSI patch is usually cropped from original HSI as the input. And 3 ×3 convolution is utilized as a key component to capture spatial features for HSI classification. However, the 3 ×3 convolution is sensitive to the spatial rotation of inputs, which results in that recent methods perform worse in rotated HSIs. To alleviate this problem, a rotation-invariant attention network (RIAN) is proposed for HSI classification. First, a center spectral attention (CSpeA) module is designed to avoid the influence of other categories of pixels to suppress redundant spectral bands. Then, a rectified spatial attention (RSpaA) module is proposed to replace 3 ×3 convolution for extracting rotation-invariant spectral-spatial features from HSI patches. The CSpeA module, the 1 ×1 convolution and the RSpaA module are utilized to build the proposed RIAN for HSI classification. Experimental results demonstrate that RIAN is invariant to the spatial rotation of HSIs and has superior performance, e.g., achieving an overall accuracy of 86.53% (1.04% improvement) on the Houston database. The codes of this work are available at https://github.com/spectralpublic/RIAN.
高光谱图像（HSI）分类是指基于HSI的光谱特征和空间信息来识别像素的土地覆盖类别。在最近基于深度学习的方法中，为了探索HSI的空间信息，通常从原始HSI中裁剪HSI补丁作为输入。并且3×3卷积被用作关键组件来捕获用于HSI分类的空间特征。然而，3×3卷积对输入的空间旋转敏感，这导致最近的方法在旋转的HSI上表现更差。为了缓解这个问题，提出了一种用于HSI分类的旋转不变注意力网络（RIAN）。首先，设计了一个中心光谱注意力（CSpeA）模块，以避免其他类别像素的影响，从而抑制冗余光谱带。然后，提出了一个校正空间注意力（RSpaA）模块来代替3×3卷积，以从HSI补丁中提取旋转不变的光谱空间特征。利用CSpeA模块、1×1卷积和RSpaA模块构建了用于HSI分类的RIAN。实验结果表明，RIAN对HSI的空间旋转具有不变性，并且具有优异的性能，例如，在休斯顿数据库上实现了86.53%的总体准确率（提高了1.04%）。这项工作的代码可在https://github.com/spectralpublic/RIAN上获取。
