Multihead Global Attention and Spatial Spectral Information Fusion for Remote Sensing Image Compression

Abstract

In recent years, convolutional neural network (CNN) based methods have been widely used in remote sensing image compression tasks. However, CNN is commonly used to extract local information and does not fully utilize global contextual information. The transformer model can effectively extract the latent contextual information in remote sensing images due to its multihead self-attention mechanisms. Due to the multiscale local features and global low-frequency information of remote sensing images, existing deep-learning-based compression methods have not effectively combined CNN and transformer. In order to overcome the limitations of the above methods, a multihead global attention and spatial spectral information fusion network (MGSSNet) is proposed for remote sensing image compression. First, a spatial spectral information fusion attention module (SSIF-AM) is constructed to obtain multiscale local information. Second, a multihead global attention module (MHG-AM) is proposed to capture rich global context information. Third, a local global collaboration module is developed to explore the correlation between the multiscale local features obtained by SSIF-AM and the global visual features obtained by MHG-AM, and to efficiently model the intrinsic relationships between them to achieve effective feature fusion. Experimental results show that compared with advanced compression models, the proposed MGSSNet method achieves better compression performance. In addition, using reconstructed images obtained by different compression methods for classification tasks has proven that the proposed method can help achieve better classification performance, indicating that the proposed compression method can more fully preserve important information in the image.

Keywords

• Attention network
• compression
• deep learning
• remote sensing images
• variational autoencoder (VAE)