Uncertainty Gates the Gradient: Adaptive Updates for Generalized Few-Shot 3D Segmentation
arXiv:2610.26909v1 Announce Type: new Abstract: In generalized few-shot 3D point cloud segmentation, support annotations are often compromised by sparsity and occlusion. Blindly adapting to such low quality samples risks learning spurious geometric patterns rather than robust novel concepts. Althou…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.CV
Uncertainty Gates the Gradient: Adaptive Updates for Generalized Few-Shot 3D Segmentation