Two-Level Feature Fusion Network for Remote Sensing Image Change Detection

This is the authors' abstract. We don't add key points for this paper.

With the advancement of satellite technology, the application space of change detection (CD) in remote sensing images is continuously expanding. However, the development of satellite remote sensing technology is still ongoing, and limited resolution and complex ground object information remain significant challenges in the field of CD. Recent CD networks generally utilize multi-feature fusion to make full use of detailed information at different scales. However, most networks have limited capabilities in handling large-scale feature maps, leading to an impact on the effectiveness in detecting detailed information. In this paper, we propose a two-level feature fusion CD network that enhances the semantic information contained in large-scale difference feature through a combination of convolutional neural network (CNN) and Transformer-based feature fusion structures. Leveraging a simple backbone network (ResNet-18) to extract dual-temporal feature maps, our model achieves better performance to mainstream state-of-the-art networks. On the LEVIR-CD, WHU-CD, and SYSU-CD datasets, we obtain F1 scores of 92.03%/92.73%/83.25%, intersection over union (IoU) of 85.24%/86.45%/71.31%, and Kappa coefficient ( <tex-math notation="LaTeX">κ</tex-math> ) of 91.61%/92.45%/78.26% respectively.