Saved in:
Bibliographic Details
Main Authors: Choi, Juhwan, Kim, YoungBin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.20012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911819049730048
author Choi, Juhwan
Kim, YoungBin
author_facet Choi, Juhwan
Kim, YoungBin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_20012
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
Choi, Juhwan
Kim, YoungBin
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2403.20012