Paper Info
Title
Learning Propagation for Arbitrarily-Structured Data
Abstract
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.
Year
DOI
Venue
2019
10.1109/ICCV.2019.00074
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Keywords
Field
DocType
CNN,SGPN,pairwise relations,point cloud segmentation,semantic segmentation networks,linear diffusion process,learned diffusion process,spatial generalized propagation networks,deep learning algorithms,data points,arbitrarily-structured data
Computer vision,Computer science,Human–computer interaction,Artificial intelligence,Data model
Conference
Volume
Issue
ISSN
2019
1
1550-5499
ISBN
Citations 
PageRank 
978-1-7281-4804-5
0
0.34
References 
Authors
14
5
Name
Order
Citations
PageRank
Sifei Liu122717.54
Xueting Li2143.22
Varun Jampani318419.44
Shalini Gupta429920.42
Jan Kautz53615198.77