mlsanityData to 7 Oct 2026

HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling

arXiv 2301.10460 ↗First posted 25 Jan 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant structural variations among the small and intricate parts. For the same reason, the necessary data annotation effort is tremendous, motivating approaches to minimize human involvement. Our labeling tool iteratively verifies or modifies part labels predicted by a deep neural network, with human feedback continually improving the network prediction. To effectively reduce human efforts, we develop two novel features in our tool, hierarchical and symmetry-aware active labeling. Our human-in-the-loop approach, coined HAL3D, achieves 100% accuracy (barring human errors) on any test set with pre-defined hierarchical part labels, with 80% time-saving over manual effort.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 52 references that are in the map. First posted on arXiv 25 Jan 2023.

Builds on

25 of 52 references.

References · 25

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2020Point Transformercited by 1,462
  5. 2020A Survey of Deep Active Learningcited by 547
  6. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  7. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  8. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  9. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  10. 2022A Comparative Survey of Deep Active Learningcited by 88
  11. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  12. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
13 more
  1. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  2. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  3. 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
  4. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  5. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  6. 2022RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structurescited by 18
  7. 2020Neural Star Domain as Primitive Representationcited by 17
  8. 2021Learning Fine-Grained Segmentation of 3D Shapes without Part Labelscited by 14
  9. 2017Learning Hierarchical Shape Segmentation and Labeling from Online Repositoriescited by 11
  10. 2022MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentationcited by 10
  11. 2018Learning to Group and Label Fine-Grained Shape Componentscited by 9
  12. 2021The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inferencecited by 4
  13. 2018A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collectionscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 20233DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognitioncited by 20
  2. 2025ASIA: Adaptive 3D Segmentation using Few Image Annotationscited by 6
  3. 2023Technical Report of 2023 ABO Fine-grained Semantic Segmentation Competitioncited by 0