Yin Yuping, Zhu Haodong, Wei Lin
Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao, Liaoning, China.
The Department of Basic Education, Liaoning Technical University, Huludao, Liaoning, China.
PLoS One. 2025 May 23;20(5):e0322345. doi: 10.1371/journal.pone.0322345. eCollection 2025.
Hyperspectral Image (HSI) classification tasks are usually impacted by Convolutional Neural Networks (CNN). Specifically, the majority of models using traditional convolutions for HSI classification tasks extract redundant information due to the convolution layer, which makes the subsequent network structure produce a large number of parameters and complex computations, so as to limit their classification effectiveness, particularly in situations with constraints on computational power and storage capacity. To address these issues, this paper proposes a lightweight multi-layer feature fusion classification method for hyperspectral images based on spatial and channel reconstruction (SCNet). Firstly, this method reduces redundant computations of spatial and spectral features by introducing Spatial and Channel Reconstruction Convolutions (SCConv), a novel convolutional compression method. Secondly, the proposed network backbone is stacked with multiple SCConv modules, which allows the network to capture spatial and spectral features that are more beneficial for hyperspectral image classification. Finally, to effectively utilize the multi-layer feature information generated by SCConv modules, a multi-layer feature fusion (MLFF) unit was designed to connect multiple feature maps at different depths, thereby obtaining a more robust feature representation. The experimental results demonstrate that, compared to seven other hyperspectral image classification methods, this network has significant advantages in terms of the number of parameters, model complexity, and testing time. These findings have been validated through experiments on four benchmark datasets.
高光谱图像（HSI）分类任务通常会受到卷积神经网络（CNN）的影响。具体而言，大多数用于HSI分类任务的使用传统卷积的模型由于卷积层会提取冗余信息，这使得后续的网络结构产生大量参数和复杂计算，从而限制了它们的分类效果，特别是在对计算能力和存储容量有约束的情况下。为了解决这些问题，本文提出了一种基于空间和通道重构的高光谱图像轻量级多层特征融合分类方法（SCNet）。首先，该方法通过引入一种新颖的卷积压缩方法——空间和通道重构卷积（SCConv）来减少空间和光谱特征的冗余计算。其次，所提出的网络主干由多个SCConv模块堆叠而成，这使得网络能够捕获对高光谱图像分类更有益的空间和光谱特征。最后，为了有效利用SCConv模块生成的多层特征信息，设计了一个多层特征融合（MLFF）单元来连接不同深度的多个特征图，从而获得更鲁棒的特征表示。实验结果表明，与其他七种高光谱图像分类方法相比，该网络在参数数量、模型复杂度和测试时间方面具有显著优势。这些发现已通过在四个基准数据集上的实验得到验证。
