Xinying Xu
Weakly supervised conditional random fields model for semantic segmentation with image patches.
Xu, Xinying; Xue, Yujing; Han, Xiaoxia; Zhang, Zhe; Xie, Jun; Ren, Jinchang
Authors
Yujing Xue
Xiaoxia Han
Zhe Zhang
Jun Xie
Professor Jinchang Ren j.ren@rgu.ac.uk
Professor of Computing Science
Abstract
Image semantic segmentation (ISS) is used to segment an image into regions with differently labeled semantic category. Most of the existing ISS methods are based on fully supervised learning, which requires pixel-level labeling for training the model. As a result, it is often very time-consuming and labor-intensive, yet still subject to manual errors and subjective inconsistency. To tackle such difficulties, a weakly supervised ISS approach is proposed, in which the challenging problem of label inference from image-level to pixel-level will be particularly addressed, using image patches and conditional random fields (CRF). An improved simple linear iterative cluster (SLIC) algorithm is employed to extract superpixels. for image segmentation. Specifically, it generates various numbers of superpixels according to different images, which can be used to guide the process of image patch extraction based on the image-level labeled information. Based on the extracted image patches, the CRF model is constructed for inferring semantic class labels, which uses the potential energy function to map from the image-level to pixel-level image labels. Finally, patch based CRF (PBCRF) model is used to accomplish the weakly supervised ISS. Experiments conducted on two publicly available benchmark datasets, MSRC and PASCAL VOC 2012, have demonstrated that our proposed algorithm can yield very promising results compared to quite a few state-of-the-art ISS methods, including some deep learning-based models.
Citation
XU, X., XUE, Y., HAN, X., ZHANG, Z., XIE, J. and REN, J. 2020. Weakly supervised conditional random fields model for semantic segmentation with image patches. Applied sciences [online], 10(5), article 1679. Available from: https://doi.org/10.3390/app10051679
Journal Article Type | Article |
---|---|
Acceptance Date | Feb 26, 2020 |
Online Publication Date | Mar 2, 2020 |
Publication Date | Mar 1, 2020 |
Deposit Date | May 6, 2022 |
Publicly Available Date | Jun 7, 2022 |
Journal | Applied sciences |
Electronic ISSN | 2076-3417 |
Publisher | MDPI |
Peer Reviewed | Peer Reviewed |
Volume | 10 |
Issue | 5 |
Article Number | 1679 |
DOI | https://doi.org/10.3390/app10051679 |
Keywords | Image semantic segmentation (ISS); Weakly supervised; Conditional random fields (CRF); Image patches |
Public URL | https://rgu-repository.worktribe.com/output/1085532 |
Files
XU 2020 Weakly supervised conditional (VOR)
(3 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by/4.0/
Copyright Statement
© 2020 by the authors. Licensee MDPI, Basel, Switzerland.
You might also like
PWDformer: deformable transformer for long-term series forecasting.
(2023)
Journal Article
Siamese residual neural network for musical shape evaluation in piano performance assessment.
(2023)
Conference Proceeding
Hyperspectral imaging based corrosion detection in nuclear packages.
(2023)
Journal Article
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search