Search Results for author: Xinxin Han

Found 2 papers, 0 papers with code

PointJEM: Self-supervised Point Cloud Understanding for Reducing Feature Redundancy via Joint Entropy Maximization

no code implementations6 Dec 2023 Xin Cao, Huan Xia, Xinxin Han, Yifan Wang, Kang Li, Linzhi Su

To reduce redundant information in the features, PointJEM maximizes the joint entropy between the different parts, thereby rendering the learned feature variables pairwise independent.

Representation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.