Sungyeon Kim

Ph.D. Candiate @ Computer Vison LAB in POSTECH.

(+82) 10-5408-3407   |   sungyeon.kim@postech.ac.kr

I am a graduate student in the Computer Science and Engineering Ph.D. program at POSTECH. My research interests are deep metric learning, representation learning and their applications. I am a member of the Computer Vision Lab at POSTECH, under supervision of Professor Suha Kwak.


Education

Computer Vision Lab, POSTECH (Pohang University of Science and Technology)

Ph.D Candidate at Computer Science and Engineering
  • Advised by Prof. Suha Kwak.
  • GPA: 3.92/4.3
  • Pohang, S.Korea
    Sep. 2018 - current

    DGIST (Daegu Gyeongbuk Institute of Science and Technology)

    B.S at Undergraduate Studies
  • GPA: 3.65/4.3
  • Daegu, S.Korea
    Mar. 2014 - Feb. 2018

    Experience

    Computer Vision Lab, POSTECH

    Research Assitant
  • Advised by Prof. Suha Kwak.
  • Researched on deep metric learning.
  • Pohang, S.Korea
    Apr. 2018 - Aug. 2018

    Vision and Learning Group, DGIST

    Undergraduate Intern
  • Researched on deep metric learning and pose estimation.
  • Daegu, S.Korea
    Dec. 2016 - Jan. 2018

    Future Automotive Technology Research Center, DGIST

    Undergraduate Intern
  • Researched on pedestrian detection in video for autonomous vehicles.
  • Implemented API for pedestrian detection utilizing PyCaffe and PyQt.
  • Daegu, S.Korea
    Jun. 2016 - Aug. 2016

    Communication and Signal Processing Lab, DGIST

    Undergraduate Intern
  • Researched on Muscle-computer connection systems and signal processing.
  • Developed Electromyography (EMG) signal processing tool to reduce signal noise.
  • Patented for rehabilitation program using measured EMG signals.
  • Daegu, S.Korea
    Mar. 2014 – Jun. 2014

    Publications

    2020

    Proxy Anchor Loss for Deep Metric Learning

    Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

    Paper Code Project Page

    2019

    Deep Metric Learning Beyond Binary Supervision

    Sungyeon Kim, Minkyo Seo, Ivan Laptev, Minsu Cho, Suha Kwak
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    (Oral Presentation, 5.6% acceptance rate)

    Paper Code Project Page

    Awards & Honors

    • Naver Ph.D Fellowship (2020)
    • Qualcomm Innovation Fellowship Korea (2020) - Deep Metric Learnign Beyond Binary Supervision
    • Grand Prize at IPIU Best Paper Award (2021) - Embedding Transfer with Label Relaxation for Improved Metric Learning