Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data

no code implementations • 19 Sep 2019 • Zhuoxun He, Lingxi Xie, Xin Chen, Ya zhang, Yan-Feng Wang, Qi Tian

Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks.

Data Augmentation Image Classification +2