5 papers
Curvilinear Structure-preserving Unpaired Cross-domain Medical Image Translation
Zihao Chen, Yi Zhou, Xudong Jiang +4
Unpaired image-to-image translation has emerged as a crucial technique in medical imaging, enabling cross-modality synthesis, domain adaptation, and data augmentation without costl…
Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
Zihao Chen, Yu Xiang, Wenyong Wang
Despite the success in learning semantically meaningful, unsupervised disentangled representations, variational autoencoders (VAEs) and their variants face a fundamental theoretica…
IIKL: Isometric Immersion Kernel Learning with Riemannian Manifold for Geometric Preservation
Zihao Chen, Wenyong Wang, Jiachen Yang +1
Geometric representation learning in preserving the intrinsic geometric and topological properties for discrete non-Euclidean data is crucial in scientific applications. Previous r…
Isometric Immersion Learning with Riemannian Geometry
Zihao Chen, Wenyong Wang, Yu Xiang
Manifold learning has been proven to be an effective method for capturing the implicitly intrinsic structure of non-Euclidean data, in which one of the primary challenges is how to…
Statistical Barriers to Affine-equivariant Estimation
Zihao Chen, Yeshwanth Cherapanamjeri
We investigate the quantitative performance of affine-equivariant estimators for robust mean estimation. As a natural stability requirement, the construction of such affine-equivar…