Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification
This addresses classification problems in remote sensing for researchers, but it is incremental as it builds on existing 3D-DenseNet models.
The paper tackled hyperspectral image classification challenges like complex object distributions and elongated features by proposing SG-DSCNet, which uses dynamic snake convolution and multi-view fusion to adaptively focus on spatial structures, achieving superior performance on IN, UP, and KSC datasets.
Deep neural networks face several challenges in hyperspectral image classification, including complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features that often lead to missing detections. To better adapt to ground object distributions and achieve adaptive dynamic feature responses while skipping redundant information, this paper proposes a Spatial-Geometry Enhanced 3D Dynamic Snake Network (SG-DSCNet) based on an improved 3D-DenseNet model. The network employs Dynamic Snake Convolution (DSCConv), which introduces deformable offsets to enhance kernel flexibility through constrained self-learning, thereby improving regional perception of ground objects. Additionally, we propose a multi-view feature fusion strategy that generates multiple morphological kernel templates from DSCConv to observe target structures from different perspectives and achieve efficient feature fusion through summarizing key characteristics. This dynamic approach enables the model to focus more flexibly on critical spatial structures when processing different regions, rather than relying on fixed receptive fields of single static kernels. The DSC module enhances model representation capability through dynamic kernel aggregation without increasing network depth or width. Experimental results demonstrate superior performance on the IN, UP, and KSC datasets, outperforming mainstream hyperspectral classification methods.