From SMOTE to Mixup for Deep Imbalanced Classification

1 code implementation • 29 Aug 2023 • Wei-Chao Cheng, Tan-Ha Mai, Hsuan-Tien Lin

Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation, a data mining approach for imbalanced learning, has been used to improve this generalization.

Classification Data Augmentation +1