Dongwon Kim

POSTECH Computer vision lab. kdwon@postech.ac.kr

prof_pic.jpeg

I am a Ph.D student at POSTECH Computer Vision Lab., supervised by Prof. Suha Kwak. I completed my B.S. in computer science and engineering also at POSTECH.

I am currently engaged in research that intersects visual perception with language understanding, focusing on object-centric representation. My aspiration is to delve into the intricacies of how visual objects can be mapped as the lexicon of a unique language, reflecting the compositional and symbolic essence of language where objects are the primary semantic units.

In line with this research interest, I have recently worked on developing effective representation schemes for cross-modal retrieval (DivE) and referring image segmentation with weak supervision (Shatter-Gather).

I am looking for the oppertunities of interesting collaborations and internship! If you are interested in my works or have any questions, please feel free to contact me.

News

Sep 26, 2024 :loudspeaker: A paper about object-centric learning is accepted at NeurIPS 2024
Jun 10, 2024 :loudspeaker: One paper is accepted at ECCV 2024
Jun 10, 2024 :loudspeaker: Joined Bytedance (San Jose, CA) as a research intern
Mar 14, 2024 :loudspeaker: Our paper about referring image segmentation has been accepted at NAACL 2024 main track.
Dec 7, 2023 :loudspeaker: I am really grateful to have been granted the POSTECHIAN fellowship!

Education

Mar, 2015 - Aug, 2019 B.S. in Computer Science & Engineering
POSTECH, Pohang, South Korea
Sep, 2019 - Present Integrated M.S & Ph.D in Computer Science & Engineering
POSTECH, Pohang, South Korea
Advisor: Prof. Suha Kwak


Selected Publications

  1. maskgen.png
    Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
    Dongwon Kim, Ju He, Qihang Yu, Chenglin Yang, Xiaohui Shen, Suha Kwak, and Liang-Chieh Chen
    In arXiv preprint, Jan 2025
  2. selfmod.png
    Bootstrapping Top-down Information for Self-modulating Slot Attention
    Dongwon Kim, Seoyeon Kim, and Suha Kwak
    In Neural Information Processing Systems (NeurIPS), Dec 2024
  3. sag.png
    Shatter and Gather: Learning Referring Image Segmentation with Text Supervision
    Dongwon Kim*, Namyup Kim*, Cuiling Lan, and Suha Kwak
    In IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
    arXiv Code Website
  4. dive.png
    Improving Cross-Modal Retrieval With Set of Diverse Embeddings
    Dongwon Kim, Namyup Kim, and Suha Kwak
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2023
    (Highlight, 235/9155 = 2.5%)
    arXiv Code Website

Professional Services

Reviewer
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022-2023
  • European Conference on Computer Vision (ECCV), 2022
  • Winter Conference on Applications of Computer Vision (WACV), 2023
  • Asian Conference on Computer Vision (ACCV), 2022

Honors and Awards

POSTECHIAN Fellowship, POSTECH, 2023
  • $5,000 grant
BK21 Best Paper Award, POSTECH GSAI, 2023
  • Self-Taught Metric Learning without Labels (CVPR 2022)
Qualcomm Innovation Fellowship Winner, Qualcomm Korea Corp., 2022
  • Self-Taught Metric Learning without Labels (CVPR 2022)
  • ReSTR: Convolution?free Referring Image Segmentation Using Transformers (CVPR 2022)
NAVER x POSTECH AI DAY The 2nd and 3rd Prize, 2022
  • ReSTR: Convolution-free Referring Image Segmentation Using Transformers (CVPR 2022)
Qualcomm Innovation Fellowship Winner, Qualcomm Korea Corp., 2021
  • Embedding Transfer with Label Relaxation for Improved Metric Learning (CVPR 2021)
IPIU Best Paper Award, 2021
  • Embedding Transfer with Label Relaxation for Improved Metric Learning (CVPR 2021)