Graph Convolutional Networks for Semi-Supervised Image Segmentation

Anna Fabijańska

doi:10.1109/ACCESS.2022.3210533

Return

Graph Convolutional Networks for Semi-Supervised Image Segmentation

2022-01-01

Anna Fabijańska *

DOI：10.1109/ACCESS.2022.3210533

Original

Original request for help

Save

Abstract

En 中文

The problem of image segmentation is one of the most significant ones in computer vision. Recently, deep-learning methods have dominated state-of-the-art solutions that automatically or interactively divide an image into subregions. However, the limitation of deep-learning approaches is that they require a substantial amount of training data, which is costly to prepare. An alternative solution is semi-supervised image segmentation. It requires rough denotations to define constraints that are next generalized to precisely delimit relevant image regions without using train examples. Among semi-supervised strategies for image segmentation, the leading are graph-based techniques that define image segmentation as a result of pixel or region affinity graph partitioning. This paper revisits the problem of graph-based image segmentation. It approaches the problem as semi-supervised node classification in the SLIC superpixels region adjacency graph using a graph convolutional network (GCN). The performance of both spectral and spatial graph convolution operators is considered, represented by Chebyshev convolution operator and GraphSAGE respectively. The results of the proposed method applied to binary and multi-label segmentation are presented, numerically assessed, and analyzed. In its best variant, the proposed method scored the average DICE of 0.86 in the binary segmentation task and 0.79 in the multi-label segmentation task. Comparison with state-of-the-art graph-based methods, including Random Walker and GrabCut, shows that graph convolutional networks can represent an attractive alternative to the existing solutions to graph-based semi-supervised image segmentation.

Keywords:

Image segmentation

Clustering methods

Convolutional neural networks

Image edge detection

Graph neural networks

Laplace equations

Semi-supervised learning

GCN

graph convolutional networks

graph node clustering

region adjacency graph