2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021
DOI: 10.1109/iccv48922.2021.00636
|View full text |Cite
|
Sign up to set email alerts
|

Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
56
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 101 publications
(57 citation statements)
references
References 29 publications
1
56
0
Order By: Relevance
“…The results in Tab. 2 show that our method exhibits much better results than GPC [14] especially in scenarios where very few annotations are available. We also reimplement popular SSL algorithms from the image segmentation domain and show their results in Tab.…”
Section: Comparative Studiesmentioning
confidence: 83%
See 3 more Smart Citations
“…The results in Tab. 2 show that our method exhibits much better results than GPC [14] especially in scenarios where very few annotations are available. We also reimplement popular SSL algorithms from the image segmentation domain and show their results in Tab.…”
Section: Comparative Studiesmentioning
confidence: 83%
“…We denote the supervised-only baseline as sup.-only. Due to the lack of LiDAR SSL works [14], we also compare SoTA consistency regularization [26,13,29] and entropy minimization [30] methods from semi-supervised image segmentation. We report the intersection-over-union (IoU) scores over each semantic class and the mean IoU (mIoU) scores over all classes in our experiments.…”
Section: Overall Pipelinementioning
confidence: 99%
See 2 more Smart Citations
“…OcCo [61] has utilized occlusion completion as a pre-training task to learn pre-train weights for point cloud analysis. However, according to our knowledge, all the existing self-supervised pre-training approaches are not efficient enough, as the majority of them need a careful treatment of negative pairs by either relying on large batch sizes [72,80], memory banks [30], data preprocessing [61] or customized mining strategies [17,30] to retrieve the negative pairs. Furthermore, their performance critically depends on complicated 3D data augmentations, e.g., cuboid [80], shape disorganizing [12] and shearing [19].…”
Section: Introductionmentioning
confidence: 99%