2023
DOI: 10.1109/lra.2022.3223558
|View full text |Cite
|
Sign up to set email alerts
|

EB-LG Module for 3D Point Cloud Classification and Segmentation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
0
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(4 citation statements)
references
References 39 publications
0
0
0
Order By: Relevance
“…1.00M 92.9 (ARM denotes adaptive rotation module, RRM denotes replacing ARM with a random rotation matrix, GAT denotes graph attention layer, without Multiview means without ARM and GAT at the same time, With XY, YZ, or XZ Plane means using MultiView but only using one of the 2D projection plane, Without XY, YZ or XZ Plane means using two of the three projection planes in MultiView. * means the method add with EBLG module [24]. The bolded text indicates the first & second high outcomes.…”
Section: A Classificationmentioning
confidence: 99%
See 1 more Smart Citation
“…1.00M 92.9 (ARM denotes adaptive rotation module, RRM denotes replacing ARM with a random rotation matrix, GAT denotes graph attention layer, without Multiview means without ARM and GAT at the same time, With XY, YZ, or XZ Plane means using MultiView but only using one of the 2D projection plane, Without XY, YZ or XZ Plane means using two of the three projection planes in MultiView. * means the method add with EBLG module [24]. The bolded text indicates the first & second high outcomes.…”
Section: A Classificationmentioning
confidence: 99%
“…We also visually compare the results of our model and DGCNN in (* means the method add with EBLG module [24]. The bolded text indicates the first & second high outcomes.…”
Section: B Part Semantic Segmentationmentioning
confidence: 99%
“…They investigated the Support-Query Mutual Attention (SQMA) module for updating support and query features, considering all support features for query feature updating. Chen et al [21] demonstrated the error feature back-projection-based local-global (EB-LG) feature-learning module to improve point-cloud representation. The EB-LG module facilitated learning hidden features between local and global features, enriching the semantic information of local features.…”
Section: Related Workmentioning
confidence: 99%
“…Masked Local 3D Structure Prediction (MLSP) [16] enables models to embed source and target data in a shared feature space, and predict masked local structure via estimating point cardinality, position and normal. Self-Supervised Boundary Point Prediction Task [17] proposes a self-supervised learning task by predicting the boundary points of masked regions to improve the prediction robustness. In particular, the self-training method has emerged as the prevailing paradigm and is frequently employed within the domain adaptation domain, such as GAST [14], GLRV [15], MLSP [16], GAI [18], DAS [19], COT [20], etc.…”
Section: Introductionmentioning
confidence: 99%