SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
arXiv:2009.01599
Abstract
Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance. However, how to do this efficiently is an open question as current approaches of utilising attention schemes or very deep models to increase the models field of view, result in complex models with large memory consumption. Inspired by recent work on graph neural networks, we propose the Self-Constructing Graph (SCG) module that learns a long-range dependency graph directly from the image and uses it to propagate contextual information efficiently to improve semantic segmentation. The module is optimised via a novel adaptive diagonal enhancement method and a variational lower bound that consists of a customized graph reconstruction term and a Kullback-Leibler divergence regularization term. When incorporated into a neural network (SCG-Net), semantic segmentation is performed in an end-to-end manner and competitive performance (mean F1-scores of 92.0% and 89.8% respectively) on the publicly available ISPRS Potsdam and Vaihingen datasets is achieved, with much fewer parameters, and at a lower computational cost compared to related pure convolutional neural network (CNN) based models.
arXiv comment11 pages, 5 figs. code will be open soon
References in corpus (12)
- Auto-Encoding Variational Bayes
- Semi-Supervised Classification with Graph Convolutional Networks
- Geometric deep learning: going beyond Euclidean data
- On the Convergence of Adam and Beyond
- Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
- Variational Graph Auto-Encoders
- Few-Shot Learning with Graph Neural Networks
- Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
- Adaptive Sampling Towards Fast Graph Representation Learning
- GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
- Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks
- Image Classification with Hierarchical Multigraph Networks