Region Mixup

This paper introduces a simple extension of mixup (Zhang et al., 2018) data augmentation to enhance generalization in visual recognition tasks. Unlike the vanilla mixup method, which blends entire images, our approach focuses on combining regions from multiple images. Mixup (Zhang et al., 2018) is a data augmentation method that trains models on weighted averages of randomly paired training points. The averaging weights are typically sampled from a beta distribution with parameter α, where α ensures that the generated training set remains close to the original dataset. Mixup-generated perturbations may adhere only to the direction towards any arbitrary data point, potentially resulting in suboptimal regularization (Guo et al., 2019).