Eungyeup Kim

PhD Student
Carnegie Mellon University
eungyeuk@cs.cmu.edu


About Me

I am a first-year PhD student in Computer Science Department at Carnegie Mellon University, advised by Prof. Zico Kolter. My research interest lies in robust ML under distribution shifts and foundation models. I did my Master's studies at Korea Advanced Institute of Science and Technology (KAIST) under Prof. Jaegul Choo.


News

[May 2022] I got admitted to PhD program in Computer Science Dept. at CMU.
[Apr 2022] I presented my work (Learning Debiased Representation via Disentangled Feature Augmentation) at SNU AIIS Retreat 2022.
[Dec 2021] I presented my work (Learning Debiased Representation via Disentangled Feature Augmentation) at NeurIPS 2021 Social: ML in Korea.
[Sep 2021] One paper is accepted as oral presentation at NeurIPS 2021.
[Aug 2021] I joined AI Lab, Kakao Enterprise as a research scientist.
[Jul 2021] Two papers (1 Oral, 1 Poster) are accepted at ICCV 2021.
[Jun 2021] I presented my work (Learning Debiased Representation via Disentangled Feature Augmentation) at Kakao Enterprise AI Lab Vision Seminar.


Publications

Learning Debiased Representation via Disentangled Feature Augmentation
Jungsoo Lee*, Eungyeup Kim*, Juyoung Lee, Jihyeon Lee, and Jaegul Choo (*: equal contributions)
Conference on Neural Information Processing Systems (NeurIPS), 2021, Virtual, Accepted as Oral Presentation (<1% acceptance rate).
[Paper] [Supplementary] [Arxiv] [Code]

Deep Edge-Aware Interactive Colorization against Color Bleeding Effects
Eungyeup Kim*, Sanghyeon Lee*, Jeonghoon Park*, Somi Choi, Choonghyun Seo, and Jaegul Choo (*: equal contributions)
IEEE International Conference on Computer Vision (ICCV), 2021, Virtual, Accepted as Oral Presentation (3% acceptance rate).
[Paper] [Supplementary] [Project] [Arxiv]

BiaSwap: Removing Dataset Bias with Bias-Tailored Swapping Augmentation
Eungyeup Kim*, Jihyeon Lee*, and Jaegul Choo (*: equal contributions)
IEEE International Conference on Computer Vision (ICCV), 2021, Virtual (25.9% acceptance rate).
[Paper] [Supplementary] [Arxiv]

Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence
Junsoo Lee*, Eungyeup Kim*, Yunsung Lee, Dongjun Kim, Jaehyuk Chang, and Jaegul Choo (*: equal contributions)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Seattle, WA (22.1% acceptance rate).
[Paper] [Supplementary] [Arxiv] [Project] [Slides] [Video]


Preprints

Unpaired Image Translation via Adaptive Convolution-based Normalization
Wonwoong Cho*, Kangyeol Kim*, Eungyeup Kim, Hyunwoo J. Kim, and Jaegul Choo (*: equal contributions)
Arxiv, 2020.
[Arxiv]