Recently, convolution neural network (CNN)-based hyperspectral image (HSI) classification has enjoyed high popularity due to its appealing performance. However, using 2-D or 3-D convolution in a standalone mode may be suboptimal in real applications. On the one hand, the 2-D convolution overlooks the spectral information in extracting feature maps. On the other hand, the 3-D convolution suffers from heavy computation in practice and seems to perform poorly in scenarios having analogous textures along with consecutive spectral bands. To solve these problems, we propose a mixed CNN with covariance pooling for HSI classification. Specifically, our network architecture starts with spectral-spatial 3-D convolutions that followed by a spatial 2-D convolution. Through this mixture operation, we fuse the feature maps generated by 3-D convolutions along the spectral bands for providing complementary information and reducing the dimension of channels. In addition, the covariance pooling technique is adopted to fully extract the second-order information from spectral-spatial feature maps. Motivated by the channel-wise attention mechanism, we further propose two principal component analysis (PCA)-involved strategies, channel-wise shift and channel-wise weighting, to highlight the importance of different spectral bands and recalibrate channel-wise feature response, which can effectively improve the classification accuracy and stability, especially in the case of limited sample size. To verify the effectiveness of the proposed model, we conduct classification experiments on three well-known HSI data sets, Indian Pines, University of Pavia, and Salinas Scene. The experimental results show that our proposal, although with less parameters, achieves better accuracy than other state-of-the-art methods.

中文翻译：

---

使用混合卷积和协方差池的高光谱图像分类

最近，基于卷积神经网络 (CNN) 的高光谱图像 (HSI) 分类因其吸引人的性能而广受欢迎。然而，在独立模式下使用 2-D 或 3-D 卷积在实际应用中可能不是最理想的。一方面，二维卷积在提取特征图时忽略了光谱信息。另一方面，3-D 卷积在实践中受到大量计算的影响，并且在具有类似纹理和连续光谱带的场景中似乎表现不佳。为了解决这些问题，我们提出了一种具有协方差池的混合 CNN 用于 HSI 分类。具体来说，我们的网络架构从光谱空间 3-D 卷积开始，然后是空间 2-D 卷积。通过这种混合操作，我们沿着光谱带融合由 3-D 卷积生成的特征图，以提供补充信息并减少通道的维度。此外，采用协方差池化技术从谱空间特征图中充分提取二阶信息。受channel-wise attention机制的启发，我们进一步提出了两种涉及主成分分析（PCA）的策略，channel-wise shift和channel-wise weighting，以突出不同光谱带的重要性并重新校准channel-wise特征响应，这可以有效提高分类准确率和稳定性，尤其是在样本量有限的情况下。为了验证所提出模型的有效性，我们对三个著名的 HSI 数据集进行了分类实验，印度松树，帕维亚大学，和萨利纳斯场景。实验结果表明，我们的提议虽然参数较少，但比其他最先进的方法实现了更好的准确性。