An Adaptive Feature Enhanced Gaussian Weighted Network for Hyperspectral Image Classification

Recently, research on hyperspectral image classification (HSIC) methods has made significant progress. However, current models commonly only focus on the primary features, overlooking the valuable information contained in secondary features that can enhance the model’s learning capabilities. To address this issue, an adaptive feature enhanced gaussian weighted network (AFGNet) is proposed in this paper. Firstly, an adaptive feature enhancement module (AFEM) was designed to evaluate the effectiveness of different features and enhance those that are more conducive to model learning. Secondly, a gaussian weighted feature fusion module (GWF2) was constructed to integrate local and global feature information effectively. Finally, a multi-head collaborative attention (MHCA) mechanism was proposed. MHCA enhances the feature extraction capability of the model for sequence data through direct interaction and global modeling. Extensive experiments were conducted on five challenging datasets. The experimental results demonstrate that the proposed method outperforms several SOTA methods.