# Self-Constructing Graph Convolutional Networks for Semantic Labeling

arXiv: https://arxiv.org/abs/2003.06932 · HTML: https://mlsanity.com/paper/2003.06932/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent](https://mlsanity.com/paper/2203.04317/) (2022)
- [Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks](https://mlsanity.com/paper/2111.03845/) (2021)
- [A Graphical Approach For Brain Haemorrhage Segmentation](https://mlsanity.com/paper/2202.06876/) (2022)
- [MFPNet: Multi-scale Feature Propagation Network For Lightweight Semantic Segmentation](https://mlsanity.com/paper/2309.04914/) (2023)

## Abstract (arXiv)

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.