Graph Convolutional Networks for Semi-Supervised Image Segmentation
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 re...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9905586/ |
| _version_ | 1797996356904681472 |
|---|---|
| author | Anna Fabijanska |
| author_facet | Anna Fabijanska |
| author_sort | Anna Fabijanska |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T10:16:18Z |
| format | Article |
| id | doaj.art-7e3ac57d7ebd47978a32be315f10c8b4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T10:16:18Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7e3ac57d7ebd47978a32be315f10c8b42022-12-22T04:29:56ZengIEEEIEEE Access2169-35362022-01-011010414410415510.1109/ACCESS.2022.32105339905586Graph Convolutional Networks for Semi-Supervised Image SegmentationAnna Fabijanska0https://orcid.org/0000-0002-0249-7247Institute of Applied Computer Science, Lodz University of Technology, Łódź, PolandThe 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.https://ieeexplore.ieee.org/document/9905586/GCNgraph convolutional networksgraph node clusteringregion adjacency graphsemi-supervised image segmentation |
| spellingShingle | Anna Fabijanska Graph Convolutional Networks for Semi-Supervised Image Segmentation IEEE Access GCN graph convolutional networks graph node clustering region adjacency graph semi-supervised image segmentation |
| title | Graph Convolutional Networks for Semi-Supervised Image Segmentation |
| title_full | Graph Convolutional Networks for Semi-Supervised Image Segmentation |
| title_fullStr | Graph Convolutional Networks for Semi-Supervised Image Segmentation |
| title_full_unstemmed | Graph Convolutional Networks for Semi-Supervised Image Segmentation |
| title_short | Graph Convolutional Networks for Semi-Supervised Image Segmentation |
| title_sort | graph convolutional networks for semi supervised image segmentation |
| topic | GCN graph convolutional networks graph node clustering region adjacency graph semi-supervised image segmentation |
| url | https://ieeexplore.ieee.org/document/9905586/ |
| work_keys_str_mv | AT annafabijanska graphconvolutionalnetworksforsemisupervisedimagesegmentation |