Dual-Layer Multi-Level Architecture and Spatial-Spectral Semantic Feature Fusion for Hyperspectral Image Classification

In recent years, using Convolutional Neural Network (CNN) for feature extraction and classification of hyperspectral image(HSI) has become a classic method. However, CNN suffer from fixed receptive fields in feature extraction, alongside the loss of shallow-level feature maps within the network. To address this issue, we propose a novel HSI classification method based on dual-layer multi-level architecture and selective kernel attention mechanism(DLMLSK). Firstly, we employ a new dual-layer network to expand the network’s receptive field, enabling the extraction of more abstract features. Secondly, a multi-level fusion module is utilized to integrate features extracted at different levels in the network, facilitating the extraction of global information. Lastly,a selective kernel(SK) attention module is introduced to perform fusion-weighted operations on the fused features, thereby enhancing the model’s selectivity towards features. Experimental results on two datasets demonstrate the effectiveness of our proposed method when compared to several standard HSI classification methods.