1. mixup: Beyond empirical risk minimization;zhang,2017
2. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
3. Fast is better than free: Revisiting adversarial training;wong,2020
4. Learning robust global representations by penalizing local predictive power;wang,2019
5. Lossy image compression with compressive autoencoders;theis,2017