no code implementations • 6 Dec 2023 • Xin Cao, Xinxin Han, Yifan Wang, Mengna Yang, Kang Li
Large and rich data is a prerequisite for effective training of deep neural networks.
no code implementations • 6 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.