Namyup Kim

Ph.D. student in the Computer Vision Lab at POSTECH.

prof_namyup.jpg

I am a Ph.D. student in Computer Science Engineering department at POSTECH, working as a member of the Computer Vision Lab, advised by Prof. Suha Kwak.

My research lies in computer vision and deep learning including, but not limited to, multimodal learning, domain generalization, weakly supervised learning and its applications. I am particularly interested in referring image segmentation which is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. If you are interested in my research projects, please feel free to contact me.

News

Oct 5, 2023 📜 A paper on weakly supervised referring image segmentation is accepted to ICCV 2023.
Mar 1, 2023 📜 A paper on cross-modal retrieval is accepted to CVPR 2023.
Feb 1, 2023 📜 A paper on domain generalization for semantic segmentation is accepted to ICRA 2023.
Nov 21, 2022 🎉 I won the NAVER Ph.D. Fellowship 2022.
Nov 7, 2022 🎉 I won the Qualcomm Innovation Fellowship 2022.
Jun 27, 2022 📜 A paper on weakly supervised learning for semantic boundary detection is accepted to IJCV.
Jun 20, 2022 📜 Two papers on domain generalization and referring image segmentation are accepted to CVPR 2022.
Mar 29, 2022 📰 Our work on referring image segmentation is featured in MSRA Highlighted Research.

Education

Mar, 2018 - 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
Mar, 2011 - Feb, 2018 Soongsil University, Seoul, South Korea
B.S. in Electronic Engineering
Advisor: Prof. Dongsung Kim

Experience

Dec, 2020 - Jun, 2021 Microsoft Research Asia (Remote), Beijing, China
Research Intern
  • Researched on domain generalization and referring image segmentation.
  • Mentor: Dr. Cuiling Lan
Mar, 2018 - Present Computer Vision Lab, POSTECH, Pohang, South Korea
Research and Teaching Assistant

Publications

  1. Improving Cross-Modal Retrieval with Set of Diverse Embeddings
    Dongwon Kim*,  Namyup Kim*, Cuiling Lan,  and Suha Kwak (*equal contribution)
    IEEE/CVF Conference on International Conference on Computer Vision (ICCV), 2023
  2. Improving Cross-Modal Retrieval with Set of Diverse Embeddings
    Dongwon Kim,  Namyup Kim,  and Suha Kwak
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  3. WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation
    Namyup Kim, Taeyoung Son, Jaehyun Pahk, Cuiling Lan, Wenjun Zeng,  and Suha Kwak
    IEEE International Conference on Robotics and Automation (ICRA), 2023
  4. ReSTR: Convolution-free Referring Image Segmentation Using Transformers
    Namyup Kim, Dongwon Kim, Cuiling Lan, Wenjun Zeng,  and Suha Kwak
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  5. Style Neophile: Constantly Seeking Novel Styles for Domain Generalization
    Juwon Kang, Sohyun Lee,  Namyup Kim,  and Suha Kwak
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  6. Learning to Detect Semantic Boundaries with Image-Level Class Labels
    Namyup Kim*, Sehyun Hwang*,  and Suha Kwak (*equal contribution)
    International Journal of Computer Vision (IJCV), 2022
  7. Urie: Universal image enhancement for visual recognition in the wild
    Taeyoung Son, Juwon Kang,  Namyup Kim, Sunghyun Cho,  and Suha Kwak
    European Conference on Computer Vision (ECCV), 2020

Honors and Awards

POSTECHIAN Fellowship Award (2022)
  • Winner ($5,000)
NAVER Ph.D. Fellowship Award (2022)
  • Winner ($4,000)
Qualcomm Innovation Fellowship South Korea (2022)
  • Winner ($3,000) - ReSTR: Convolution‑free Referring Image Segmentation Using Transformers (CVPR2022)
NAVER \(\times\) POSTECH AI DAY (2022)
  • The 2\(^{\textnormal{nd}}\) and 3\(^{\textnormal{rd}}\) Prize - ReSTR: Convolution‑free Referring Image Segmentation Using Transformers (CVPR2022)
The 26th HumanTech Paper Award, Samsung Electronics Co., Ltd. (2020)
  • The Honorable Mention ($3,000) - Learning to Detect Semantic Boundaries with Image‑Level Class Labels (IJCV2022)