Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention

03/01/2022
by   Haoyi Xiu, et al.
0

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module.

READ FULL TEXT

page 1

page 4

page 9

research
09/21/2022

3DPCT: 3D Point Cloud Transformer with Dual Self-attention

Transformers have resulted in remarkable achievements in the field of im...
research
11/14/2021

Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation

With the proliferation of Lidar sensors and 3D vision cameras, 3D point ...
research
07/07/2021

GA-NET: Global Attention Network for Point Cloud Semantic Segmentation

How to learn long-range dependencies from 3D point clouds is a challengi...
research
06/07/2019

PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation

With the tide of artificial intelligence, we try to apply deep learning ...
research
03/08/2023

DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds

Local features and contextual dependencies are crucial for 3D point clou...
research
09/25/2019

Learning Propagation for Arbitrarily-structured Data

Processing an input signal that contains arbitrary structures, e.g., sup...

Please sign up or login with your details

Forgot password? Click here to reset