Junsuk Choe

Associate Professor

Seoul, South Korea
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Junsuk Choe is an Associate Professor in the Department of Computer Science and Engineering at Sogang University with nine years of experience spanning academia and industry research. His work focuses on computer vision and machine learning, particularly methods that learn effectively from limited data via self-supervised and weakly-supervised approaches. Before joining Sogang’s faculty he was a research scientist at NAVER AI Lab, bringing practical AI development experience to his academic research and teaching. He holds a Ph.D. in Integrated Technology and a B.S. in Electrical and Electronic Engineering from Yonsei University, reflecting deep interdisciplinary training. Based in Seoul, he blends rigorous research with applied problem-solving, often bridging theory and real-world deployment in Korean AI ecosystems. An underappreciated strength is his sustained focus on data-efficient learning, positioning him to advance ML where labeled data is scarce.
code9 years of coding experience
job5 years of employment as a software developer
bookPh.D., Integrated Technology, Ph.D., Integrated Technology at Yonsei University
languagesEnglish, Korean
github-logo-circle

Github Skills (18)

weakly-supervised-learning10
reinforcement-learning9
localization9
deep-learning8
robustness8
tensorflow8
machine-learning8
generalization7
receptive-field7
transfer-learning6
representation-learning6
convolutional-neural-networks6
imagenet5
pytorch4
multi-gpu4

Programming languages (2)

Jupyter NotebookPython

Github contributions (5)

github-logo-circle
junsukchoe/co-localization

May 2018 - Jul 2018

Contributions:2 PRs, 267 pushes, 9 branches in 1 month
junsukchoe/ADL

Jun 2019 - Feb 2020

Attention-based Dropout Layer for Weakly Supervised Object Localization (CVPR 2019 Oral)
Contributions:1 PR, 67 pushes, 1 branch in 7 months
localizationweakly-supervised-learningobject-localizationclass-activation-map
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial