← Search

Changsheng Sun

2 accepted papers

2024

PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification

AAAI 2024technical

With the growth of 3D sensing technology, the deep learning system for 3D point clouds has become increasingly important, especially in applications such as autonomous vehicles where safety is a primary concern. However, there are growing concerns about the reliability of these systems when they enc…

2020

Digraph Inception Convolutional Networks

NeurIPS 2020poster

Graph Convolutional Networks (GCNs) have shown promising results in modeling graph-structured data. However, they have difficulty with processing digraphs because of two reasons: 1) transforming directed to undirected graph to guarantee the symmetry of graph Laplacian is not reasonable since it not…