Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning

Juhwan Choi, YoungBin Kim

Keywords: Data augmentation, Image classification

TL;DR: Image data augmentation can benefit from curriculum learning.

Abstract: Data augmentation is one of the regularization strategies for the training of deep learning models, which enhances generalizability and prevents overfitting, leading to performance improvement. Although researchers have proposed various data augmentation techniques, they often lack consideration for the difficulty of augmented data. Recently, another line of research suggests incorporating the concept of curriculum learning with data augmentation in the field of natural language processing. In this study, we adopt curriculum data augmentation for image data augmentation and propose **colorful cutout**, which gradually increases the noise and difficulty introduced in the augmented image. Our experimental results highlight the possibility of curriculum data augmentation for image data. We publicly released our source code to improve the reproducibility of our study.

Submission Number: 11