Kang Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Kang Song has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Hongming Zhou
College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, China
1 shared publication- Qiusuo Qian
College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, China
1 shared publication Wenyong Gui
College of Mathematics, Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 325035, China
1 shared publication- Xianglei Zhang
College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, China
1 shared publication
Latest Publications
- Open Access
- 29 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 42745-42756
WAILS: Watershed Algorithm With Image-Level Supervision for Weakly Supervised Semantic Segmentation
Image semantic segmentation has great development in many fields, the lack of fully-supervised segmentation labels has always been a major problem in the development of image semantic segmentation. In this paper, we propose a WAILS method to solve this problem. First, the image is coarsely segmented through a weakly supervised network at the image level. Second, to further obtain the shape of the target in the image, the watershed algorithm is used to refine the result of the coarse segmentation. Third, this refined image is used as a label for the first round of training of a fully-supervised image semantic segmentation network. Last, the results are refined through the watershed, as the label of the second round of fully-supervised training, and then it iterates. This method achieves pixel-level semantic segmentation only through image-level labels and watershed pre-segmentation. Our method achieved good performance on the PASCAL 2012 dataset and COCO dataset, while its segmentation accuracy surpasses all current weakly supervised semantic segmentation models in the category of bird, airplane, sheep and so on.
- 29 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 42745-42756
Open AccessWAILS: Watershed Algorithm With Image-Level Supervision for Weakly Supervised Semantic Segmentation
Image semantic segmentation has great development in many fields, the lack of fully-supervised segmentation labels has always been a major problem in the development of image semantic segmentation. In this paper, we propose a WAILS method to solve this problem. First, the image is coarsely segmented through a weakly supervised network at the image level. Second, to further obtain the shape of the target in the image, the watershed algorithm is used to refine the result of the coarse segmentation. Third, this refined image is used as a label for the first round of training of a fully-supervised image semantic segmentation network. Last, the results are refined through the watershed, as the label of the second round of fully-supervised training, and then it iterates. This method achieves pixel-level semantic segmentation only through image-level labels and watershed pre-segmentation. Our method achieved good performance on the PASCAL 2012 dataset and COCO dataset, while its segmentation accuracy surpasses all current weakly supervised semantic segmentation models in the category of bird, airplane, sheep and so on.