Shan Yu

CKDF: Cascaded Knowledge Distillation Framework for Robust Incremental Learning

2022 · IEEE Transactions on Image Processing

Recently, owing to the superior performances, knowledge distillation-based (kd-based) methods with the exemplar rehearsal have been widely applied in class incremental learning (CIL). However, we discover that they suffer from the feature uncalibration problem, which …

Boosting AI-Generated Biomedical Images with Confidence through Advanced Statistical Inference

2025 · Journal of the American Statistical Association

Generative artificial intelligence (AI) has transformed the biomedical imaging field through image synthesis, addressing challenges of data availability, privacy, and diversity in biomedical research. This paper proposes a novel nonparametric method within the functional data …