Class-Aware Self- and Cross-Attention Network for Few-Shot Semantic Segmentation of Remote Sensing Images

Abstract

Few-Shot Semantic Segmentation (FSS) has drawn massive attention recently due to its remarkable ability to segment novel-class objects given only a handful of support samples. However, current FSS methods mainly focus on natural images and pay little attention to more practical and challenging scenarios, e.g., remote sensing image segmentation. In the field of remote sensing image analysis, the characteristics of remote sensing images, like complex backgrounds and tiny foreground objects, make novel-class segmentation challenging. To cope with these obstacles, we propose a Class-Aware Self- and Cross-Attention Network (CSCANet) for FSS in remote sensing imagery, consisting of a lightweight self-attention module and a supervised prior-guided cross-attention module. Concretely, the self-attention module abstracts robust unseen-class information from support features, while the cross-attention module generates a superior quality query attention map for directing the network to focus on novel objects. Experiments demonstrate that our CSCANet achieves outstanding performance on the standard remote sensing FSS benchmark iSAID-5i, surpassing the existing state-of-the-art FSS models across all combinations of backbone networks and K-shot settings.