View : 181 Download: 0
Contour-Aware Equipotential Learning for Semantic Segmentation
- Title
- Contour-Aware Equipotential Learning for Semantic Segmentation
- Authors
- Yin, Xu; Min, Dongbo; Huo, Yuchi; Yoon, Sung-Eui
- Ewha Authors
- 민동보
- SCOPUS Author ID
- 민동보
- Issue Date
- 2023
- Journal Title
- IEEE TRANSACTIONS ON MULTIMEDIA
- ISSN
- 1520-9210
1941-0077
- Citation
- IEEE TRANSACTIONS ON MULTIMEDIA vol. 25, pp. 6146 - 6156
- Keywords
- Category-level contour learning; semantic boundary refinement; supervised semantic segmentation
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- Abstract
- With increasing demands for high-quality semantic segmentation in the industry, hard-distinguishing semantic boundaries have posed a significant threat to existing solutions. Inspired by real-life experience, i.e., combining varied observations contributes to higher visual recognition confidence, we present the equipotential learning (EPL) method. This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions. The conversion to the potential domain is implemented via a lightweight differentiable anisotropic convolution without incurring any parameter overhead. Besides, the designed two loss functions, the point loss and the equipotential line loss implement anisotropic field regression and category-level contour learning, respectively, enhancing prediction consistencies in the inter/intra-class boundary areas. More importantly, EPL is agnostic to network architectures, and thus it can be plugged into most existing segmentation models. This paper is the first attempt to address the boundary segmentation problem with field regression and contour learning. Meaningful performance improvements on Pascal Voc 2012 and Cityscapes demonstrate that the proposed EPL module can benefit the off-the-shelf fully convolutional network models when recognizing semantic boundary areas. Besides, intensive comparisons and analysis show the favorable merits of EPL for distinguishing semantically-similar and irregular-shaped categories.
- DOI
- 10.1109/TMM.2022.3205441
- Appears in Collections:
- 인공지능대학 > 컴퓨터공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML