Self-Constructing Graph Convolutional Networks for Semantic Labeling
This addresses the limitation of Graph Neural Networks in semantic labeling tasks where prior graphs are unavailable, offering a more efficient solution for aerial imagery analysis.
The paper tackles the problem of semantic labeling in aerial imagery without relying on manually constructed prior graphs by proposing a Self-Constructing Graph (SCG) architecture that automatically generates optimized non-local context graphs from input features. The model achieves competitive F1-scores on the ISPRS Vaihingen dataset with fewer parameters and lower computational cost compared to CNN-based methods.
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.