Graph Neural Networks (GNNs) have received increasing attention in many
fields. However, due to the lack of prior graphs, their use for semantic
labeling has been limited. Here, we propose a novel architecture called the
Self-Constructing Graph (SCG), which makes use of learnable latent variables to
generate embeddings and to self-construct the underlying graphs directly from
the input features without relying on manually built prior knowledge graphs.
SCG can automatically obtain optimized non-local context graphs from
complex-shaped objects in aerial imagery. We optimize SCG via an adaptive
diagonal enhancement method and a variational lower bound that consists of a
customized graph reconstruction term and a Kullback-Leibler divergence
regularization term. We demonstrate the effectiveness and flexibility of the
proposed SCG on the publicly available ISPRS Vaihingen dataset and our model
SCG-Net achieves competitive results in terms of F1-score with much fewer
parameters and at a lower computational cost compared to related pure-CNN based
work. Our code will be made public soon.

提出了一种名为 Self-Constructing Graph (SCG) 的新型体系结构，利用可学习的潜变量直接从输入特征生成嵌入并自行构建底层图，从而自动获取来自航空图像中复杂物体的优化的非局部上下文图。通过自适应对角线增强方法和一个变分下限来优化 SCG，该下限由一个定制的图重构项和一个 Kullback-Leibler 分歧得到规则化项。SCG 在公开的 ISPRS Vaihingen 数据集上表现出有效性和灵活性，和纯 CNN 模型相比，在参数和计算成本上具有明显优势。