HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification

arXiv:2404.00272v1 Announce Type: new
Abstract: Classifying hyperspectral images is a difficult task in remote sensing, due to their complex high-dimensional data. To address this challenge, we propose HSIMamba, a novel framework that uses bidirectional reversed convolutional neural network pathways to extract spectral features more efficiently. Additionally, it incorporates a specialized block for spatial analysis. Our approach combines the operational efficiency of CNNs with the dynamic feature extraction capability of attention mechanisms found in Transformers. However, it avoids the associated high …

abstract arxiv challenge classification convolutional neural network cs.cv data extract feature features framework images imaging network neural network novel sensing space state type