A novel 3D shape classification algorithm: point-to-vector capsule network

Ye, Hailiang; Du, Zijin; Cao, Feilong

doi:10.1007/s00521-021-06231-z

Cited by 3 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Point cloud classification using traditional machine learning methods [10] suffers from long training times and poor classification accuracy. The rapid development of deep learning technology [11] over the past decade coupled with the emergence of 3D model datasets (such as ShapeNet [12], ModelNet [13], PASCAL3D+ [14], and the Stanford Computer Vision and Geometry Laboratory datasets) has resulted in new approaches to classifying 3D point cloud data. The purpose of our research is to improve the accuracy of point cloud classification.…”

Section: Introductionmentioning

confidence: 99%

Multi-view attention-convolution pooling network for 3D point cloud classification

Wang

Cai

2021

Appl Intell

View full text Add to dashboard Cite

Classifying 3D point clouds is an important and challenging task in computer vision. Currently, classification methods using multiple views lose characteristic or detail information during the representation or processing of views. For this reason, we propose a multi-view attention-convolution pooling network framework for 3D point cloud classification tasks. This framework uses Res2Net to extract the features from multiple 2D views. Our attention-convolution pooling method finds more useful information in the input data related to the current output, effectively solving the problem of feature information loss caused by feature representation and the detail information loss during dimensionality reduction. Finally, we obtain the probability distribution of the model to be classified using a full connection layer and the softmax function. The experimental results show that our framework achieves higher classification accuracy and better performance than other contemporary methods using the ModelNet40 dataset.

show abstract

Section: Introductionmentioning

confidence: 99%