EUVIMEDEUVIMED entdecken
Crossref

Joint‐Learning: A Robust Segmentation Method for 3D Point Clouds Under Label Noise

Mengyao Zhang, Jie Zhou, Tingyun Miao, Yong Zhao, Xin Si, Jingliang Zhang

Computer Animation and Virtual Worlds · 2025-05 · 36 (3)

DOI: 10.1002/cav.70038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Animation and Virtual Worlds, 2025-06. Verfasst von Mengyao Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Qingdao Municipality, Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most of point cloud segmentation methods are based on clean datasets and are easily affected by label noise. We present a novel method called Joint‐learning, which is the first attempt to apply a dual‐network framework to point cloud segmentation with noisy labels. Two networks are trained simultaneously, and each network selects clean samples to update its peer network. The communication between two networks is able to exchange the knowledge they learned, possessing good robustness and generalization ability. Subsequently, adaptive sample selection is proposed to maximize the learning capacity. When the accuracies of both networks are no longer improving, the selection rate is reduced, which results in cleaner selected samples. To further reduce the impact of noisy labels, for unselected samples, we provide a joint label correction algorithm to rectify their labels via two networks' predictions. We conduct various experiments on S3DIS and ScanNet‐v2 datasets under different types and rates of noises. Both quantitative and qualitative results verify the reasonableness and effectiveness of the proposed method. By comparison, our method is substantially superior to the state‐of‐the‐art methods and achieves the best results in all noise settings. The average performance improvement is more than 7.43%, with a maximum of 11.42%.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Qingdao Municipality
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Zhang, M., Zhou, J., Miao, T., Zhao, Y., Si, X., & Zhang, J. (2025). Joint‐Learning: A Robust Segmentation Method for 3D Point Clouds Under Label Noise. Computer Animation and Virtual Worlds, 36(3). https://doi.org/10.1002/cav.70038

Vancouver

Zhang M, Zhou J, Miao T, Zhao Y, Si X, Zhang J. Joint‐Learning: A Robust Segmentation Method for 3D Point Clouds Under Label Noise. Computer Animation and Virtual Worlds. 2025;36(3). doi:10.1002/cav.70038

BibTeX
@article{Zhang2025,
  author = {Zhang, Mengyao and Zhou, Jie and Miao, Tingyun and Zhao, Yong and Si, Xin and Zhang, Jingliang},
  title = {Joint‐Learning: A Robust Segmentation Method for 3D Point Clouds Under Label Noise},
  journal = {Computer Animation and Virtual Worlds},
  year = {2025},
  volume = {36},
  number = {3},
  doi = {10.1002/cav.70038}
}
Kostenlos starten →