Xuan Zhao

On the Information Theoretic Distance Measures and Bidirectional Helmholtz Machines

2018 · arXiv (Cornell University)

By establishing a connection between bi-directional Helmholtz machines and information theory, we propose a generalized Helmholtz machine. Theoretical and experimental results show that given \textit{shallow} architectures, the generalized model outperforms the previous ones substantially.

Invariant Content Synergistic Learning for Domain Generalization on Medical Image Segmentation

2022 · 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Although deep convolution neural networks (DC-NNs) can achieve remarkable success on medical image segmentation, their performance might significantly deteriorate when confronting testing data with the new distribution. Recent studies suggest that one major cause of …