IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

1 code implementation • NeurIPS 2023 • Zhenglin Huang, Xiaoan Bao, Na Zhang, Qingqi Zhang, Xiaomei Tu, Biao Wu, Xi Yang

Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting.

Anomaly Detection Data Augmentation