For hyperspectral remote sensing image (HSI) classification, the learning process of deep neural networks has been progressively advanced in depth, but the fine features are often largely lost or even disappear in the process of depth transfer. With the increase in feature aggregation and connectivity, the complexity of the network and the training parameters increases greatly, requiring more training time. This paper proposed a multi-scale dense network (MSDN) for HSI classification that made full use of different scale information in the network structure and combined scale information throughout the network. It implemented feature extraction of HSIs in two dimensions, including the features at fine and coarse levels. In the horizontal direction, it considered the deep extraction of HSI features, and the 3-D dense connection structure was used for aggregating features at different levels. In the vertical direction, scale information was considered, and three-scale feature maps at low, middle, and high levels were generated based on the first layer of the network. The MSDN used stride convolution for downsampling and combined feature information at different scale levels. The MSDN extracted features along the diagonal line. The network implemented the reconstruction of deep feature extraction and multi-scale fusion for HSI classification. The MSDN model performed well on representative HSI datasets, namely, the Indian Pines, Pavia University, Salinas, Botswana, and Kennedy Space Center datasets. It improved the training speed and accuracy for HSI classification and especially improved the convergence speed, which effectively saved computing resources and had high stability.

Hyperspectral remote sensing images (HSIs) are rich in spectral-spatial information. The deep learning models can help to automatically extract and discover these rich information from HSIs for classifying HSIs. However, the sampling of the models and the design of the hyperparameters depend on the number of samples and the size of each sample's input space. In the case of limited samples, the description dimension of features is also limited and overfitting to other remote sensing image datasets is evident. This study proposes a novel deep feature aggregation network (DFAN) for HSI classification based on a 3D-convolutional neural network (3D-CNN) from the perspective of feature aggregation patterns. By introducing the residual learning and dense connectivity strategies, we established a deep feature residual network (DFRN) and a deep feature dense network (DFDN) to exploit the low-, middle- and high-level features in HSIs. For the Indian Pines and Kennedy Space Center datasets, the DFRN model was determined to be more accurate. On the Pavia University dataset, both the DFDN and DFRN have basically the same accuracy, but the DFDN has faster convergence speed and more stable performance on the validation set than the DFRN. Therefore, when faced with different HSI data, the corresponding aggregation method can be chosen more flexibly according to the requirements on number of training samples and the convergence speed. This is beneficial in HSI classification.

Deep neural networks face several challenges in hyperspectral image classification, including high-dimensional data, sparse distribution of ground objects, and spectral redundancy, which often lead to classification overfitting and limited generalization capability. To more effectively extract and fuse spatial context with fine spectral information in hyperspectral image (HSI) classification, this paper proposes a novel network architecture called STNet. The core advantage of STNet stems from the dual innovative design of its Spatial-Spectral Transformer module: first, the fundamental explicit decoupling of spatial and spectral attention ensures targeted capture of key information in HSI; second, two functionally distinct gating mechanisms perform intelligent regulation at both the fusion level of attention flows (adaptive attention fusion gating) and the internal level of feature transformation (GFFN). This characteristic demonstrates superior feature extraction and fusion capabilities compared to traditional convolutional neural networks, while reducing overfitting risks in small-sample and high-noise scenarios. STNet enhances model representation capability without increasing network depth or width. The proposed method demonstrates superior performance on IN, UP, and KSC datasets, outperforming mainstream hyperspectral image classification approaches.