SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
This work addresses the challenge of high memory consumption in semantic segmentation models for remote sensing applications, offering an incremental improvement in efficiency.
The paper tackles the problem of efficiently capturing global contextual representations for semantic segmentation by proposing a Self-Constructing Graph module that learns long-range dependencies directly from images, achieving competitive performance with mean F1-scores of 92.0% and 89.8% on ISPRS Potsdam and Vaihingen datasets while reducing parameters and computational cost compared to CNN-based models.
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.