Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization

Page view(s)
21
Checked on Mar 26, 2024
Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization
Title:
Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization
Journal Title:
2021 IEEE International Conference on Image Processing (ICIP)
Keywords:
Publication Date:
23 August 2021
Citation:
Liao, Y., Zhu, H., Chen, T., & Fan, J. (2021). Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization. 2021 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip42928.2021.9506359
Abstract:
Point cloud instance segmentation is steadily improving with the development of deep learning. However, current progress is hindered by the expensive cost of collecting dense point cloud labels. To this end, we propose the first semi-supervised point cloud instance segmentation architecture, which is called semi-supervised point cloud instance segmentation with perturbation consistency regularization (SPCR). It is capable to alleviate the data-hungry bottleneck of existing strongly supervised methods. Specifically, SPCR enforces an invariance of the predictions over different perturbations applied to the input point clouds. We firstly introduce various perturbation schemes on inputs to force the network to be robust and easily generalized to the unseen and unlabeled data. Further, perturbation consistency regularization is then conducted on predicted instance masks from various transformed inputs to provide self-supervision for network learning. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the state-of-the-art of fully supervised methods.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Fund
Grant Reference no. : A18A2b0046

This work is supported by National Natural Science Foundation of China (No. 62071127 and U1909207), Shanghai Pujiang Program (No.19PJ1402000), Shanghai Municipal Science and Technology Major Project (No.2021SHZDZX0103), Shanghai Engineering Research Center of AI Robotics and Engineering Research Center of AI Robotics, Ministry of Education in China
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
ISSN:
2381-8549
Files uploaded:

File Size Format Action
spcr.pdf 425.10 KB PDF Open