Jaedong Hwang

Master's Student

Electrical and Computer Engineering

Seoul National University

: jd730snu.ac.kr

: jd730  : jaedong_hwang

About

I am a master's student at Computer Vision Lab (advisor: Prof. Bohyung Han), Seoul National University (SNU). From June, 2020 to September 2020, I am doing an internship at Adobe Research under the guidance of Dr. Joong-Young Lee. During undergraduate study, I worked as a research intern at the lab and T-Brain. I also have spent great time with Prof. Joseph Lim at the University of Southern California and Prof. Byoung-Tak Zhang at BioIntelligence Lab, SNU

My research interests come from a question, "How people can learn from small amounts of data or coarse data such as noisy or weak-labeled data and why machine cannot?" My goal is applying cognitive science to machine learning vice versa to dig into this question. Meanwhile, I am also interested in machine learning approaches to solve this question. Shortly, I am interested in three fields as follows:

  • Cognitive Science: curiosity, procedural memory
  • Computer Vision: action recognition/localization, weakly-supervised instance segmentation, openset/long-tailed recognition
  • Reinforcement Learning: exploration strategies, dynamics randomization

News

  • [06/2020] I joined Adobe Research @ Remote (due to COVID-19) as a Deep Learning Research Intern mentored by Joong-Young Lee
  • [09/2019] I joined Computer Vision Lab @ Seoul National University as a Master's student advised by Professor Bohyung Han
  • [10/2018] One paper "Robust harmonic field based tooth segmentation in real-life noisy scanned mesh" is accepted to SPIE Medical Imaging (@San Diego, Feb 2019)
  • [09/2018] I joined Computer Vision Lab @ Seoul National University as a Research Intern advised by Professor Bohyung Han
  • [05/2018] I joined T-Brain @ SKT, Seoul, Korea, as a Research Intern

Education

Seoul National University
 Master's Student in ECE (Advisor: Bohyung Han)
Sep 2019 - Present
Seoul National University
 B.S. in Computer Science and Engineering (minor: Brain-Mind-Behavior)
(Summa Cum Laude)
Mar 2013 - Aug 2019
(Apr 2015- Jan 2017 : Military Service)

Academic Experience

Computer Vision Lab,   Seoul National University,   Korea
 Research Intern, Advisor : Bohyung Han

Developed an end-to-end weakly-supervised instance segmentation framework via object detection.

Sep 2018 - Aug 2019
CLVR Lab,   University of Southern California,   CA
 Visitng Student, Advisor : Joseph Lim

Developed a demonstration quality assement framework via Meta-Learning.

Mar 2018 - May 2018
BioIntelligence Lab,   Seoul National University,   Korea
 Research Intern, Advisor : Byoung-Tak Zhang

Developed a discourse system acting as a cashier using Hidden Markov Model.

Jul 2014 - Apr 2015

Industrial Experience

Adobe Research,  Adobe Inc.,   CA (remote)
 Deep Learning Research Intern, Mentor: Joong-Young Lee
Jun 2020 - Sep 2020
(expected)
T-Brain,   SKT,   Korea
 Research Intern
Developed a demonstration suitability assessment framework for imitation learning leveraging Model-Agnostic Meta-Learning (MAML).
Jun 2018 - Aug 2018
Cybercrime Investigation Unit,   Seoul Metropolitan Police Agency,   Korea
 Investigator (Auxiliary Police) - as a substitute of military service
Investigated and arrested criminals regarding illegal cyber gambling (approximately $2.5 billion), malware, hacking, and illegal explosive maker.
Aug 2015 - Jan 2017

Publications

Weakly Supervised Instance Segmentation by Community Learning
Jaedong Hwang*, Seohyun Kim*, Jeany Son, Bohyung Han.
 arXiv. 2020. [arxiv].

Robust harmonic field based tooth segmentation in real-life noisy scanned mesh
Jaedong Hwang*, Sanghyeok Park*, Seokjin Lee*, Yeong-Gil Shin.
SPIE 10949, Medical Imaging 2019: Image Processing. [paper], [poster]

An adaptive computational discourse system based on data-driven learning algorithm
 Seungwon Lee*, Jaedong Hwang*, Eunsol Kim, Byoung-Tak Zhang.
International Symposium on advanced Intelligent Systems (ISIS 2015) (Vol. 201). [paper]
Best Session Paper Awards

(*: equally contributed)

Awards & Honors

  • Best Paper of Brain-Mind-Behavior department
    2017
  • Seoul Metropolitan Police Agency Award Certificate
    2016
  • ISIS 2015 Best Session Paper Award
    2015
  • Jongha Fellowship
    2014

Scholarship

Seoam Scholarship Foundation (Merit-based)
A full scholarship for undergraduate studies and additional stipends of $200 each month (from 2018, stipends are increased to $350)
Sep 2013 - Aug 2019

Services

Reviewer
ECCV 2020
Volunteer
ICLR 2020
Teaching Assistant
035.001 Digital Computer Concept and Practice (Instructor: Bohyung Han)

Other Projects

Meta-Learned Suitability Assessor for Noisy Demonstration Sets
 Advisor : Joseph Lim
This project is for making a framework that selects suitable demonstration subsets in a noisy demonstraiton set including unsuitable demonstrations via meta learning. The model is able to automatically rank the suitability of given demonstrations so that it can learn from the most suitable subset. [paper], [project page]

Mar 2018 - Oct 2018
Style Recognition of Artworks
This project is a final project of undergraduate course, "Computer Vision(M 1522.001000, prof. Gun Hee Kim)" from March to June. According to the project, Using SVM and PCA with featured layer of CNN is better than using Deep Neural Network only. Accuracy of style recognition is higher than human expert.

Mar 2017 - Jun 2017

Other Experience

Seoul National University Philharmonic Orchestra
 Server Administrator
Aug 2016 - Present
 Chief of department of Data Management
Oct 2014 - Mar 2015
 2nd Violinist
Mar 2013 - Aug 2019
National Museum of Modern and Contemporary Art, Seoul, Korea
 Volunteer
Mar 2017 - Oct 2017
Guahm Middle School, Seoul, Korea
 Mentor
Sep 2013 - Feb 2015

Online Coursework

Statistical Learning(Stanford Online) with Distinction
2016
Mining Massive Datasets (Coursera) with Distinction
2015
Machine Learning (Coursera)
2014