Dongwan Kim

About

Hi! I'm a 4th year PhD student at the SNU Computer Vision Lab, advised by Bohyung Han. I'm interested in problems encountered in real-world applications of deep neural networks, such as continual learning, domain adaptation/generalization, and efficient architectures.

Contact: dongwan123 (at) gmail (dot) com 

Updates

[February 2023] Our paper on the stability-plasticity dilemma in class-incremental learning will be presented at CVPR 2023.

[November 2022] Our paper, UniSeg, was selected for the Qualcomm Innovation Fellowship Korea 2022.  

[July 2022] Our paper on training a single semantic segmentation model from multiple datasets has been accepted at ECCV 2022.

Work Experience

Research Internship at NEC Labs America

Research Internship at Naver Labs

Publications (Chronological order)

Dongwan Kim, Yi-Hsuan Tsai, Yumin Suh, Masoud Faraki, Sparsh Garg, Manmohan Chandraker, and Bohyung Han

ECCV 2022

Recipient of the Qualcomm Innovation Fellowship Korea 2022 Award

Sanghyeok Chu, Dongwan Kim, and Bohyung Han

NeurIPS 2021

Seungmin Lee*, Dongwan Kim*, and Bohyung Han 

(* denotes equal contribution)

CVPR 2021 

[code]

Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jongwoo Han, and Bohyung Han

ECCV 2020

Seungmin Lee*, Dongwan Kim*, Namil Kim, and Seong-Gyun Jeong

(* denotes equal contribution)

ICCV 2019

[code]

Review Experience

Conferences

Journals