Learning Propagation for Arbitrarily-structured Data

09/25/2019
by   Sifei Liu, et al.
1

Processing an input signal that contains arbitrary structures, e.g., superpixels and point clouds, remains a big challenge in computer vision. Linear diffusion, an effective model for image processing, has been recently integrated with deep learning algorithms. In this paper, we propose to learn pairwise relations among data points in a global fashion to improve semantic segmentation with arbitrarily-structured data, through spatial generalized propagation networks (SGPN). The network propagates information on a group of graphs, which represent the arbitrarily-structured data, through a learned, linear diffusion process. The module is flexible to be embedded and jointly trained with many types of networks, e.g., CNNs. We experiment with semantic segmentation networks, where we use our propagation module to jointly train on different data -- images, superpixels and point clouds. We show that SGPN consistently improves the performance of both pixel and point cloud segmentation, compared to networks that do not contain this module. Our method suggests an effective way to model the global pairwise relations for arbitrarily-structured data.

READ FULL TEXT

page 7

page 8

page 13

page 14

page 15

research
09/19/2021

Efficient Urban-scale Point Clouds Segmentation with BEV Projection

Point clouds analysis has grasped researchers' eyes in recent years, whi...
research
10/12/2022

LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLAD

Large-scale point cloud semantic segmentation is an important task in 3D...
research
10/02/2018

Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

In this paper, we present a deep learning architecture which addresses t...
research
08/27/2021

Learning Inner-Group Relations on Point Clouds

The prevalence of relation networks in computer vision is in stark contr...
research
08/07/2022

Global Hierarchical Attention for 3D Point Cloud Analysis

We propose a new attention mechanism, called Global Hierarchical Attenti...
research
03/06/2019

Fast Graph Representation Learning with PyTorch Geometric

We introduce PyTorch Geometric, a library for deep learning on irregular...
research
03/01/2022

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

We present a simple but effective attention named the unary-pairwise att...

Please sign up or login with your details

Forgot password? Click here to reset