16 citations · 22 across the 12 of their papers we have counts for
6 papers · 1 filter
Self Identity Mapping
Xiuding Cai, Yaoyao Zhu, Linjie Fu +2
Regularization is essential in deep learning to enhance generalization and mitigate overfitting. However, conventional techniques often rely on heuristics, making them less reliabl…
Learning Semantic Directions for Feature Augmentation in Domain-Generalized Medical Segmentation
Yingkai Wang, Yaoyao Zhu, Xiuding Cai +3
Medical image segmentation plays a crucial role in clinical workflows, but domain shift often leads to performance degradation when models are applied to unseen clinical domains. T…
Semantic Data Augmentation Enhanced Invariant Risk Minimization for Medical Image Domain Generalization
Yaoyao Zhu, Xiuding Cai, Yingkai Wang +3
Deep learning has achieved remarkable success in medical image classification. However, its clinical application is often hindered by data heterogeneity caused by variations in sca…
Invariance Principle Meets Vicinal Risk Minimization
Yaoyao Zhu, Xiuding Cai, Yingkai Wang +3
Deep learning models excel in computer vision tasks but often fail to generalize to out-of-distribution (OOD) domains. Invariant Risk Minimization (IRM) aims to address OOD general…
BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification
Yaoyao Zhu, Xiuding Cai, Xueyao Wang +3
Data augmentation is a crucial regularization technique for deep neural networks, particularly in medical image classification. Mainstream data augmentation (DA) methods are usuall…
Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation
Xiuding Cai, Yaoyao Zhu, Dong Miao +2
In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutio…