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

Chen, Jintao; Zhang, Yan; Ma, Feifan; Tan, Zhuangbin

doi:10.1109/lra.2022.3223558

Cited by 12 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

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

Adaptive Multiview Graph Convolutional Network for 3D Point Cloud Classification and Segmentation

Niu,

Wang,

Zhuang

2024

Preprint

View full text Add to dashboard Cite

show abstract

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%

Adaptive Multiview Graph Convolutional Network for 3D Point Cloud Classification and Segmentation

Niu,

Wang,

Zhuang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

Contribution of Geometric Feature Analysis for Deep Learning Classification Algorithms of Urban LiDAR Data

Tarsha Kurdi,

Amakhchan,

Gharineiat

et al. 2023

Sensors

View full text Add to dashboard Cite

The use of a Machine Learning (ML) classification algorithm to classify airborne urban Light Detection And Ranging (LiDAR) point clouds into main classes such as buildings, terrain, and vegetation has been widely accepted. This paper assesses two strategies to enhance the effectiveness of the Deep Learning (DL) classification algorithm. Two ML classification approaches are developed and compared in this context. These approaches utilize the DL Pipeline Network (DLPN), which is tailored to minimize classification errors and maximize accuracy. The geometric features calculated from a point and its neighborhood are analyzed to select the features that will be used in the input layer of the classification algorithm. To evaluate the contribution of the proposed approach, five point-clouds datasets with different urban typologies and ground topography are employed. These point clouds exhibit variations in point density, accuracy, and the type of aircraft used (drone and plane). This diversity in the tested point clouds enables the assessment of the algorithm’s efficiency. The obtained high classification accuracy between 89% and 98% confirms the efficacy of the developed algorithm. Finally, the results of the adopted algorithm are compared with both rule-based and ML algorithms, providing insights into the positioning of DL classification algorithms among other strategies suggested in the literature.

show abstract

“…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%

PointADAM: Unsupervised Adversarial Domain Adaptation on Point Clouds With Metric Learning via Compact Feature Representation

Lu,

Yap,

Khor

2024

IEEE Access

View full text Add to dashboard Cite

Domain adaptation can mitigate the problem of limited labels in deep learning training. Nevertheless, extending the 2D domain adaptation method directly to 3D encounters challenges unique to point clouds, frequently resulting in inadequate feature alignment and a lack of discriminative features for decision boundaries. In light of this, we propose an unsupervised adversarial domain adaptation with metric learning (PointADAM) via compact feature representation. PointADAM is a two-stage architecture. In the first stage, it extracts high-level semantic and low-level local features from source and target domains based on the geometric relations of point cloud neighbors. Subsequently, it aligns the features from the two domains in an unsupervised adversarial manner, thereby obtaining a shared common feature space. In the second stage, a self-training method is employed to label the target domain with pseudo-labels. It is followed by selecting target domain samples with high confidence. To enhance discriminative feature learning, joint supervision is employed through both cross-entropy loss and center loss. Cross-entropy is utilized to calculate the probability of each category for classification and center loss is utilized to compact intra-class distribution and disperse inter-class distance, thereby improving classification accuracy by optimizing the decision boundary. Experimental results on the PointDA-10 dataset illustrate that our method performs relatively better than the state-of-the-art methods for domain adaptation on the point cloud by 3.1% in accuracy.

show abstract

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

Cited by 12 publications

References 39 publications

Adaptive Multiview Graph Convolutional Network for 3D Point Cloud Classification and Segmentation

Adaptive Multiview Graph Convolutional Network for 3D Point Cloud Classification and Segmentation

Contribution of Geometric Feature Analysis for Deep Learning Classification Algorithms of Urban LiDAR Data

PointADAM: Unsupervised Adversarial Domain Adaptation on Point Clouds With Metric Learning via Compact Feature Representation

Contact Info

Product

Resources

About