부산대학교 도서관

Deep learning has been utilized for hyperspectral image (HSI) classification in recent years, with notable performance improvements. In particular, convolutional neural networks (CNNs) methods have achieved major advancements in this area. However, there are some drawbacks to the existing CNN-based HSI classification approaches: 1) the lack of effective and simple feature representations in CNNs, which overlook the effects of spectral differences and spatial contextual information; 2) the classification model has an enormous network complexity as a result of its numerous training parameters and high computational requirements; and 3) the category samples in HSI data exhibit a significant long tail distribution issue, which affects the classification performance of HSI. To address these issues, we propose a lightweight spectral–spatial neural architecture with multiattention feature extraction (LSSMA) for HSI classification. The main work consists of three areas: 1) A spectral feature extraction and fusing module is created to facilitate the fusing of spectral–spatial features while reducing the number of trainable parameters and computational complexity of the model. This module uses convolutions of various kernel sizes for residual connection and feature fusion, and introduces group convolution to achieve efficient feature representation. 2) To utilize the spectral–spatial correlation of HSI data to its fullest, a multiscale convolutional activation guided attention mechanism is designed and the position attention module is referenced, which can capture spectral differences and spatial contextual relationships between ground objects. and 3) Focal loss is applied in computer vision tasks to the LSSMA model to enhance its capacity to handle category imbalance. Experimental results on four publicly available hyperspectral datasets show that the method obtains better classification performance at a lower computational cost.