LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Chenxi, Chen, Nuo, Tan, Fengyun, Chen, Yantong, Yuan, Bochun, Li, Tianrui, Li, Chongshou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909634511503360
author Li, Chenxi
Chen, Nuo
Tan, Fengyun
Chen, Yantong
Yuan, Bochun
Li, Tianrui
Li, Chongshou
author_facet Li, Chenxi
Chen, Nuo
Tan, Fengyun
Chen, Yantong
Yuan, Bochun
Li, Tianrui
Li, Chongshou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning
Li, Chenxi
Chen, Nuo
Tan, Fengyun
Chen, Yantong
Yuan, Bochun
Li, Tianrui
Li, Chongshou
Computer Vision and Pattern Recognition
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.
title LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.18924