Shouqiang Kang
Biographic Data
| ID | 9966413 |
|---|---|
| NAME | Shouqiang Kang |
| GIVEN NAMES | Shouqiang |
| FAMILY NAME | Kang |
| SIGNATURE | KANG S |
| AFFILIATIONS | Harbin University of Science and Technology |
| VERIFIED | No |
| TOTAL WORKS | 1 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 1 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2026 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
Evidentially Driven Uncertainty Decomposition for Weakly Supervised Point Cloud Semantic Segmentation
Point cloud semantic segmentation is a core component in indoor scene understanding and autonomous driving. Under weak point-level supervision, only a small subset of points is annotated, making effective use of unlabeled points critical yet non-trivial. Many existing approaches rely on prediction confidence to filter pseudo labels or enforce consistency, which can bias training toward easy points and amplify early mistakes. Consequently, confide…
No prominent works on this page.
Evidentially Driven Uncertainty Decomposition for Weakly Supervised Point Cloud Semantic Segmentation
Point cloud semantic segmentation is a core component in indoor scene understanding and autonomous driving. Under weak point-level supervision, only a small subset of points is annotated, making effective use of unlabeled points critical yet non-trivial. Many existing approaches rely on prediction confidence to filter pseudo labels or enforce consistency, which can bias training toward easy points and amplify early mistakes. Consequently, confide…
3D Shape Modeling and Analysis (1 work) · 3D Surveying and Cultural Heritage (1 work) · Decision boundary (1 work) · Point cloud (1 work) · Robotics and Sensor-Based Localization (1 work) · Segmentation (1 work)