AttPNet: Attention-Based Deep Neural Network for 3D Point Set Analysis
1
Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA
2
Department of Computer Science, University of California, Irvine, CA 92697, USA
3
Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(19), 5455; https://doi.org/10.3390/s20195455
Received: 14 August 2020 / Revised: 8 September 2020 / Accepted: 8 September 2020 / Published: 23 September 2020
(This article belongs to the Special Issue 3D Images, Point Clouds and Videos Classification and Management by Means of Artificial Intelligence Approaches from Industrial to Agriculture Applications)
Point set is a major type of 3D structure representation format characterized by its data availability and compactness. Most former deep learning-based point set models pay equal attention to different point set regions and channels, thus having limited ability in focusing on small regions and specific channels that are important for characterizing the object of interest. In this paper, we introduce a novel model named Attention-based Point Network (AttPNet). It uses attention mechanism for both global feature masking and channel weighting to focus on characteristic regions and channels. There are two branches in our model. The first branch calculates an attention mask for every point. The second branch uses convolution layers to abstract global features from point sets, where channel attention block is adapted to focus on important channels. Evaluations on the ModelNet40 benchmark dataset show that our model outperforms the existing best model in classification tasks by 0.7% without voting. In addition, experiments on augmented data demonstrate that our model is robust to rotational perturbations and missing points. We also design a Electron Cryo-Tomography (ECT) point cloud dataset and further demonstrate our model’s ability in dealing with fine-grained structures on the ECT dataset.
View Full-Text
Keywords:
point cloud; attention mechanism; deep neural network
▼
Show Figures
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Yang, Y.; Ma, Y.; Zhang, J.; Gao, X.; Xu, M. AttPNet: Attention-Based Deep Neural Network for 3D Point Set Analysis. Sensors 2020, 20, 5455.
AMA Style
Yang Y, Ma Y, Zhang J, Gao X, Xu M. AttPNet: Attention-Based Deep Neural Network for 3D Point Set Analysis. Sensors. 2020; 20(19):5455.
Chicago/Turabian StyleYang, Yufeng; Ma, Yixiao; Zhang, Jing; Gao, Xin; Xu, Min. 2020. "AttPNet: Attention-Based Deep Neural Network for 3D Point Set Analysis" Sensors 20, no. 19: 5455.
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
Search more from Scilit