LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning
This work addresses the challenge of efficient annotation for 3D vision tasks, offering a novel approach that could reduce labeling costs, though it is incremental in combining LLMs with active learning.
The paper tackles the problem of 3D point cloud semantic segmentation with limited annotation by integrating large language models to create hierarchical label structures and guide uncertainty-based sample selection, achieving up to 4% mIoU improvement under extremely low annotation budgets like 0.02%.
We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection. Unlike prior methods that treat labels as flat and independent, our approach leverages LLM prompting to automatically generate multi-level semantic taxonomies and introduces a recursive uncertainty projection mechanism that propagates uncertainty across hierarchy levels. This enables spatially diverse, label-aware point selection that respects the inherent semantic structure of 3D scenes. Experiments on S3DIS and ScanNet v2 show that our method achieves up to 4% mIoU improvement under extremely low annotation budgets (e.g., 0.02%), substantially outperforming existing baselines. Our results highlight the untapped potential of LLMs as knowledge priors in 3D vision and establish hierarchical uncertainty modeling as a powerful paradigm for efficient point cloud annotation.