Page
%P
-
Chapter and Conference Paper
Synthetic Minority with CutMix for Imbalanced Image Classification
The class-imbalanced distributions between different classes in the visual world pose great challenges for deep learning-based classification models particularly on correct prediction of minority classes. In t...
-
Chapter and Conference Paper
Alleviating Data Imbalance Issue with Perturbed Input During Inference
Intelligent diagnosis is often biased toward common diseases due to data imbalance between common and rare diseases. Such bias may still exist even after applying re-balancing strategies during model training....