Learning with Noisy Labels for Robust Point Cloud Segmentation

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

37 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF International Conference on Computer Vision
Subtitle of host publicationICCV 2021
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages6423-6432
ISBN (electronic)9781665428125
ISBN (print)978-1-6654-2813-2
Publication statusPublished - Oct 2021

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499
ISSN (electronic)2380-7504

Conference

Title18th IEEE/CVF International Conference on Computer Vision (ICCV 2021)
LocationVirtual
PlaceCanada
CityMontreal
Period11 - 17 October 2021

Abstract

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current deep learning methods based on the clean label assumptions may fail with noisy labels. Yet, object class labels are often mislabeled in real-world point cloud datasets. In this work, we take the lead in solving this issue by proposing a novel Point Noise-Adaptive Learning (PNAL) framework. Compared to existing noise-robust methods on image tasks, our PNAL is noise-rate blind, to cope with the spatially variant noise rate problem specific to point clouds . Specifically, we propose a novel point-wise confidence selection to obtain reliable labels based on the historical predictions of each point. A novel cluster-wise label correction is proposed with a voting strategy to generate the best possible label taking the neighbor point correlations into consideration. We conduct extensive experiments to demonstrate the effectiveness of PNAL on both synthetic and real-world noisy datasets. In particular, even with 60% symmetric noisy labels, our proposed method produces much better results than its baseline counterpart without PNAL and is comparable to the ideal upper bound trained on a completely clean dataset. Moreover, we fully re-labeled the validation set of a popular but noisy real-world scene dataset ScanNetV2 to make it clean, for rigorous experiment and future research. Our code and data will be released.

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

Learning with Noisy Labels for Robust Point Cloud Segmentation. / Ye, Shuquan; Chen, Dongdong; Han, Songfang et al.
Proceedings - 2021 IEEE/CVF International Conference on Computer Vision: ICCV 2021. Institute of Electrical and Electronics Engineers, Inc., 2021. p. 6423-6432 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review