1. BG-Net: boundary-guidance network for object consistency maintaining in semantic segmentation.
- Author
-
Cheng, Xiji, Huang, Shiliang, Liao, Bingyan, Wang, Yayun, and Luo, Xiao
- Subjects
GEOMETRIC modeling ,PIXELS ,BEAM steering - Abstract
Semantic segmentation suffers from boundary shift and shape deformation problems due to the neglect of overall guidance information. Motivated by that the object boundaries have a stronger representation for overall information of target objects, we propose a simple yet effective network, boundary-guidance network (BG-Net), for object consistency maintaining in semantic segmentation. In our work, we explore the pixels both near and far from the boundary, characterizing each pixel by utilizing pixel-boundary association. The boundary feature is integrated into the segmentation feature to mitigate boundary shift and shape deformation problem. We explicitly supervise the angle and distance information of pixels pointing to the nearest object boundary. Then the association can be learned by geometric modelling. Meanwhile, the low-level feature emphasized up-sampling (LFEU) module is designed to supplement the detail representation in high-level feature without direct interference. Finally, we evaluate our method on Cityscapes and CamVid datasets. The experimental results demonstrate the superiority of our BG-Net. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF