Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches
Open Access
- 2 March 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (5), 1679
- https://doi.org/10.3390/app10051679
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.Funding Information
- National Natural Science Foundation of China (21606159)
- Natural Science Foundation of Shanxi Province (201801D121144, 201801D221190)
- Shanxi Provincial Key Research and Development Project (201803D121039)
This publication has 33 references indexed in Scilit:
- Weakly-supervised region annotation for understanding scene imagesMultimedia Tools and Applications, 2014
- Background Prior-Based Salient Object Detection via Deep Reconstruction ResidualIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature LearningIEEE Transactions on Geoscience and Remote Sensing, 2014
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Interactive image segmentation by maximal similarity based region mergingPattern Recognition, 2010
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- A review on image segmentation techniquesPattern Recognition, 1993
- Watersheds in digital spaces: an efficient algorithm based on immersion simulationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991