Dual Feature Aggregation Network for Hyperspectral Image Classification

Recent hyperspectral image (HSI) classification works have focused on developing a promising architecture by combining convolutional neural networks (CNNs) with Transformers. However, most of them fail to consider the interactive fusion of global and local features, thus significantly limiting the HSI classification performance. To address this problem, in this article, we propose a dual feature aggregation network (DFAN) for HSI classification tasks. It effectively aggregates local and global spatial-spectral features to achieve efficient classification. Specifically, we design a dual feature aggregation (DFA) module to extract and aggregate local and global spatial-spectral features. In this module, the lightweight local block is responsible for extracting local spatial-spectral features, and the global block is used to extract global spatial-spectral features and aggregation tasks. Concretely, the token local aggregation multilayer perceptron (TLA-MLP) module in the global block is to extract spatial-position-aware and spectral-channel-aware global discriminative information. Meanwhile, it learns multiscale neighboring token features by aggregating token local neighborhood features. In addition, we employ the local self-global aggregation block to learn the global aggregation features and then fuse them with the local spatial-spectral features. Afterward, the cross-attention aggregation of local and global spatial-spectral features is used to further improve the classification ability of our proposed model. The experimental results on three benchmark datasets show that our proposed DFAN method outperforms other state-of-the-art HSI classification methods.