Mixed Samples Data Augmentation with Replacing Latent Vector Components in Normalizing Flow

GENKI OSADA, Budrul Ahsan, Takashi Nishide

Keywords: Data augmentation, Normalizing flow

Abstract:

Data augmentation mixing two samples has been acknowledged as an effective regularization method for various deep neural network models. Given that images mixed by popular methods (e.g., MixUp and CutMix) are unnatural to the human eye, we hypothesized that generating more natural images could achieve better performance as data augmentation.
To verify this, we propose a new mixing method that synthesizes images in which two source images coexist naturally.
Our method performs a mixing operation in latent space through a normalizing flow, and the key is how to mix two latent vectors.
We preliminarily observed that there exists a dependency between the dimensions in input space and those in latent space in transformation with normalizing flows. Based on this observation, we designed our mixing scheme in latent space. We show that our method yields visually natural augmented images and improves classification performance.