Changhwa Park

108, Yeoui-daero

Seoul, Republic of Korea

I received the B.S. and M.S. degree in electrical and computer engineering from Seoul National University, Seoul, South Korea, in 2019 and 2021.

From 2021 to 2022, I was an AI researcher at AIRS Company and 42dot Inc., Hyundai Motor Group. I am currently a machine learning engineer at LG Energy Solution.

My research interests include deep learning, imbalanced data, anomaly detection, and domain adaptation.

news

Jan 16, 2023	Joined LG Energy Solution as a machine learning engineer.
Oct 19, 2022	Website is opened!
Sep 19, 2022	Joined 42dot Inc., Hyundai Motor Group as a machine learning engineer.
Mar 3, 2021	Joined AIRS Company, Hyundai Motor Group as an AI researcher.

selected publications

Removing Undesirable Feature Contributions Using Out-of-Distribution Data

Saehyung Lee, Changhwa Park, Hyungyu Lee, and 3 more authors

In International Conference on Learning Representations, 2021

Abs Bib HTML

Several data augmentation methods deploy unlabeled-in-distribution (UID) data to bridge the gap between the training and inference of neural networks. However, these methods have clear limitations in terms of availability of UID data and dependence of algorithms on pseudo-labels. Herein, we propose a data augmentation method to improve generalization in both adversarial and standard learning by using out-of-distribution (OOD) data that are devoid of the abovementioned issues. We show how to improve generalization theoretically using OOD data in each learning scenario and complement our theoretical analysis with experiments on CIFAR-10, CIFAR-100, and a subset of ImageNet. The results indicate that undesirable features are shared even among image data that seem to have little correlation from a human point of view. We also present the advantages of the proposed method through comparison with other data augmentation methods, which can be used in the absence of UID data. Furthermore, we demonstrate that the proposed method can further improve the existing state-of-the-art adversarial training.
@inproceedings{lee2021removing, title = {Removing Undesirable Feature Contributions Using Out-of-Distribution Data}, author = {Lee, Saehyung and Park, Changhwa and Lee, Hyungyu and Yi, Jihun and Lee, Jonghyun and Yoon, Sungroh}, booktitle = {International Conference on Learning Representations}, year = {2021}, url = {https://openreview.net/forum?id=eIHYL6fpbkA}, }
Mutual Learning for Long-Tailed Recognition

Changhwa Park, Junho Yim, and Eunji Jun

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2023

Abs Bib HTML

Deep neural networks perform well in artificially-balanced datasets, but real-world data often has a long-tailed distribution. Recent studies have focused on developing unbiased classifiers to improve tail class performance. Despite the efforts to learn a fine classifier, we cannot guarantee a solid performance if the representations are of poor quality. However, learning high-quality representations in a long-tailed setting is difficult because the features of tail classes easily overfit the training dataset. In this work, we propose a mutual learning framework that generates high-quality representations in long-tailed settings by exchanging information between networks. We show that the proposed method can improve representation quality and establish a new state-of-the-art record on several long-tailed recognition benchmark datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
@inproceedings{park2022mutual, title = {Mutual Learning for Long-Tailed Recognition}, author = {Park, Changhwa and Yim, Junho and Jun, Eunji}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = jan, year = {2023}, }