Research map / Label-efficient and robust learning / Recognition and long-tail
HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling
Fenggen Yu, Yiming Qian, Francisca Gil-Ureta, Brian Jackson, Eric Bennett, Hao Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hierarchical labeling to active learning (ablation) | HAL3D · PartNet Chair | labeling time (h): 5.99 -> 4.34 | Improved |
| add hierarchical labeling to active learning (ablation) | HAL3D · PartNet Chair | part label accuracy: 89.84 -> 94.13 | Improved |
| add symmetry checking (ablation) | HAL3D · PartNet Chair | labeling time (h): 5.21 -> 4.34 | Improved |
| add active learning fine-tuning to hierarchical symmetry-aware labeling (ablation) | HAL3D · PartNet Chair | labeling time (h): 6.37 -> 4.34 | Improved |
| add proposal network before manual modification (ablation) | manual labeling · PartNet Chair | labeling time (h): 22.05 -> 8.65 | Improved |
| use proposal network instead of NGSP for initial labels | HAL3D · PartNet inference time, Chair | seconds per shape: 5.410 -> 0.012 | Improved |
| use proposal network instead of NGSP for initial labels | HAL3D · PartNet Chair | part label accuracy: 68.98 -> 67.45 | Hurt |
| use HAL3D instead of correcting PartNet or NGSP predictions manually | ABO annotation · ABO Chair | labeling time (h): 28.30 -> 6.46 | Improved |
Closest papers by meaning
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.87)
- PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding (CVPR 2019 · similarity 0.87)
- PartField: Learning 3D Feature Fields for Part Segmentation and Beyond (ICCV 2025 · similarity 0.86)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.86)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.85)
- Activating Sparse Part Concepts for 3D Class Incremental Learning (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
