Hierarchical Relation Learning for Few-Shot Semantic Segmentation in Remote Sensing Images

Xin He, Yun Liu, Yong Zhou, Henghui Ding, Jiaqi Zhao, Bing Liu, Xudong Jiang

Abstract: Few-shot semantic segmentation (FSS) aims to segment specific semantic classes in a query image using only a few annotated support samples. While FSS has gained significant attention in natural image processing, it remains underexplored in the more challenging domain of remote sensing images (RSIs). Existing FSS approaches for RSIs primarily focus on enhancing feature representations of support or query images through hierarchical/multilevel feature fusion. However, unlike fully supervised segmentation that relies on feature extraction and optimization, FSS requires segmenting the query image based on its relations with annotated support images. To address this need, we propose the concept of hierarchical relation learning (HRL) to explore the intrinsic support-query relations, allowing for the direct refinement of target object appearances in the query image. Specifically, we propose a hierarchical relation network (HRNet), which performs single-scale relation extraction (SRE) at each network hierarchy and multiscale relation aggregation (MRA) across hierarchies. In addition, we construct a bidirectional hierarchical loss (BHLoss) to guide HRNet training, providing targeted supervision at each hierarchy in both top-down and bottom-up directions, thus facilitating robust multiscale relation learning across hierarchies. Comprehensive experiments on the iSAID- $5^{i}$ , DLRSD- $5^{i}$ , and LoveDA- $2^{i}$ datasets demonstrate the superiority of the proposed HRL. The code will be available at https://github.com/XinnHe/HRL

External IDs:dblp:journals/tgrs/HeLZDZLJ25