Donghyeon Kwon

profile.jpg

I am a 5th-year Ph.D. candidate in the Department of Computer Science and Engineering at POSTECH, working in the Computer Vision Lab under the supervision of Prof. Suha Kwak. My research focuses on advancing data-efficient methods in computer vision and deep learning, particularly in areas such as multi-modal knowledge distillation, semi- and self-supervised learning, and their practical applications.

My work aims to push the boundaries of what is possible with limited data, enabling more scalable and accessible solutions in computer vision. I am passionate about bridging the gap between cutting-edge research and real-world impact through these techniques. If you’re interested in my research projects or potential collaborations, I’d be happy to connect—feel free to reach out!





News

Jan 23, 2025 📝 Our paper on domain-generalizable sementic segmentation is accepted to ICLR 2025.
Jan 21, 2025 :trophy: Our paper on semi-supervised learning has been selected for an oral presentation at WACV 2025.
Oct 28, 2024 :trophy: I got a Samsung Ph.D. Sponsorship (DS) from Samsung Advanced Institude of Technology (SAIT).
Aug 31, 2024 📝 Our paper on semi-supervised learning is accepted to WACV 2025.
Oct 20, 2023 📝 Our paper on self-supervised learning using web videos is accepted to WACV 2024.


Experiences

July, 2023 - Aug, 2023 Samsung Advanced Institute of Technology, Suwon, S.Korea.
Research Intern
  • Conducted research on data-efficient 3D object detection for autonomous driving scenes.
  • Mentor: Dr. Hyeongseok Son
Feb, 2021 - Present Computer Vision Lab, POSTECH, Pohang, S.Korea
Research and Teaching Assistant
Jun, 2019 - Aug, 2019 Korea Institute of Science and Technology, Seoul, S.Korea.
Research Assistant
  • Conducted research on typo correction for virtual keyboards.
  • Advisor: Dr. Suhyun Kim


Education

Feb, 2021 - Present Pohang University of Science and Technology (POSTECH), Pohang, South Korea
Integrated M.S. & Ph.D. Student in Computer Science and Engineering
Advisor: Prof. Suha Kwak.
Currently working at POSTECH Computer Vision Lab.
Feb, 2017 - Feb, 2021 Pohang University of Science and Technology (POSTECH), Pohang, South Korea
B.S in Computer Science and Engineering
Advisor: Prof. Hwanjo Yu.


Publications

2025

  1. pahk_iclr25.png
    Decoupled Finetuning for Domain Generalizable Semantic Segmentation
    Jaehyun Pahk, Donghyeon Kwon, Seong Joon Oh, and Suha Kwak
    In The Thirteenth International Conference on Learning Representations (ICLR), Apr 2025
  2. kwon_wacv25.png
    Boosting Semi-Supervised Video Action Detection with Temporal Context
    Donghyeon Kwon, Inho Kim, and Suha Kwak
    In Proceedings of the Winter Conference on Applications of Computer Vision (WACV), Feb 2025
    Oral Presentation

2024

  1. kwon_wacv24.png
    Self-Supervised Learning of Semantic Correspondence Using Web Videos
    Donghyeon Kwon, Minsu Cho, and Suha Kwak
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024

2023

  1. kang_icml23.png
    Leveraging Proxy of Training Data for Test-Time Adaptation
    Juwon Kang, Nayeong Kim, Donghyeon Kwon, Jungseul Ok, and Suha Kwak
    In International Conference on Machine Learning (ICML), Jul 2023

2022

  1. kwon_cvpr22.png
    Semi-Supervised Semantic Segmentation With Error Localization Network
    Donghyeon Kwon, and Suha Kwak
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2022


Professional Services

Conference Reviewer
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 - 2025
  • International Conference on Computer Vision (ICCV), 2023
  • European Conference on Computer Vision (ECCV), 2024
  • Conference on Neural Information Processing Systems (NeurIPS), 2023
  • International Conference on Learning Representations (ICLR), 2024 - 2025
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
  • AAAI Conference on Artificial Intelligence (AAAI), 2024
  • Asian Conference on Computer Vision (ACCV), 2022, 2024


Honors and Awards