In this paper, we propose a Boundary-aware Graph Reasoning (BGR) module to learn long-range contextual features for semantic segmentation. Rather than directly construct the graph based on the backbone features, our BGR module explores a reasonable way to combine segmentation erroneous regions with the graph construction scenario. Motivated by the fact that most hard-to-segment pixels broadly distribute on boundary regions, our BGR module uses the boundary score map as prior knowledge to intensify the graph node connections and thereby guide the graph reasoning focus on boundary regions. In addition, we employ an efficient graph convolution implementation to reduce the computational cost, which benefits the integration of our BGR module into current segmentation backbones. Extensive experiments on three challenging segmentation benchmarks demonstrate the effectiveness of our proposed BGR module for semantic segmentation.

翻译：在本文中,我们提出一个边界意识图解解析模块(BGR)模块,以学习用于语义分解的长距离背景特征。我们BGR模块不是直接构建基于主干线特征的图解,而是探索一种合理的方式,将偏差区块与图形构造情景相结合。我们BGR模块的动机是,大多数难以分解的像素在边境地区广泛分布,因此,我们BGR模块使用边界评分地图作为先前的知识,以强化图形节点连接,从而指导图表推理重点的边界区域。此外,我们使用高效的图解变动实施来降低计算成本,这有利于将我们的BGR模块纳入当前的分解主干线。关于三个具有挑战性的分解基准的大规模实验显示了我们提议的用于语义分解的BGR模块的有效性。