One Class One Click: Quasi scene-level weakly supervised point cloud semantic segmentation with active learning

Puzuo Wang, Wei Yao, Jie Shao

Research output: Journal article publicationJournal articleAcademic researchpeer-review

3 Citations (Scopus)


Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed and contribute to attaining competitive results under weak supervision strategy. Revisiting current weak label forms, we introduce One Class One Click (OCOC), a low cost yet informative quasi scene-level label, which encapsulates both point-level and scene-level annotations. An active weakly supervised framework is proposed to leverage scarce labels by involving weak supervision from both global and local perspectives. Contextual constraints are imposed by an auxiliary scene classification task, respectively based on global feature embedding and point-wise prediction aggregation, which restricts the model prediction merely to OCOC labels within a sub-cloud. Furthermore, we design a context-aware pseudo labeling strategy, which effectively supplement point-level supervisory signals subject to OCOC labels. Finally, an active learning scheme with a uncertainty measure — temporal output discrepancy is integrated to examine informative samples and provides guidance on sub-clouds query, which is conducive to quickly attaining desirable OCOC annotations and reduces the labeling cost to an extremely low extent. Extensive experimental analysis using three LiDAR benchmarks respectively collected from airborne, mobile and ground platforms demonstrates that our proposed method achieves very promising results though subject to scarce labels. It considerably outperforms genuine scene-level weakly supervised methods by up to 25% in terms of average F1 score and achieves competitive results against full supervision schemes. On terrestrial LiDAR dataset — Semantics3D, using approximately 2‱ of labels, our method achieves an average F1 score of 85.2%, which increases by 11.58% compared to the baseline model. Codes are publicly available at

Original languageEnglish
Pages (from-to)89-104
Number of pages16
JournalISPRS Journal of Photogrammetry and Remote Sensing
Publication statusPublished - Oct 2023


  • Active learning
  • Point cloud
  • Semantic segmentation
  • Weakly supervised learning

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Computer Science Applications
  • Computers in Earth Sciences


Dive into the research topics of 'One Class One Click: Quasi scene-level weakly supervised point cloud semantic segmentation with active learning'. Together they form a unique fingerprint.

Cite this