Enhancing robustness of point cloud semantic segmentation against adversarial attacks using silhouette coefficient regularized neural ODEs
This dissertation aims to enhance the robustness of point cloud semantic seg mentation against adversarial attacks by proposing an improved defense mech anism. The primary focus is on developing a novel model, termed Silhou ette Coefficient Regularization Augmented Stable Neural ODE with Lyapunov St...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2025
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/182637 |