4 papers
Test-time Adaptation of Pelvic Bone Segmentation Models via Dynamic Reliability-Guided
Ling Ren, Chao Deng, Ziming Wang +2
Reliable pelvic bone segmentation (PBS) from CT is essential for robot-assisted pelvic trauma surgery, yet deploying a source-trained model to a new hospital suffers from severe pe…
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation
Junjie Chen, Yuecong Xu, Haosheng Li +1
3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving, enabling precise scene understanding through po…
Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks
Haosheng Li, Junjie Chen, Yuecong Xu +1
Unsupervised domain adaptation (UDA) frameworks have shown good generalization capabilities for 3D point cloud semantic segmentation models on clean data. However, existing works o…
ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation
Haosheng Li, Yuecong Xu, Junjie Chen +1
3D point cloud semantic segmentation technology has been widely used. However, in real-world scenarios, the environment is evolving. Thus, offline-trained segmentation models may l…