Hyundo Lee
I am currently a MS/PhD student at Seoul National University,
advised by Byoung-Tak Zhang .
I earned my Bachelor's degree in Department of Computer Science and Engineering from Seoul National University.
I'm interested in self-supervised representation learning and generative models in the vision domain, and applications to robotics.
Email  / 
Google Scholar  / 
Github
|
|
Education
- (2019.03 - current) MS/Ph.D in Computer Science and Engineering, Seoul National University
- (2014.03 - 2019.02) BS in Computer Science and Engineering (Minored in Physics and Astronomy),
Seoul National University
- (2012.02 - 2014.02) Highschool, Daegu Il Science High School
|
|
DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning
Won-Seok Choi, Hyundo Lee, Dong-Sig Han, Junseok Park, Heeyeon Koo, Byoung-Tak Zhang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024
We propose an active data filtering process during self-supervised pre-training in our novel framework, Duplicate Elimination (DUEL). This framework integrates an active memory inspired by human working memory and introduces distinctiveness information.
[PDF]
|
|
Learning Geometry-aware Representations by Sketching
Hyundo Lee,
Inwoo Hwang,
Hyunsung Go,
Won-Seok Choi,
Kibeom Kim,
Byoung-Tak Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
2023
Inspired by human behavior that depicts an image by sketching, we propose a novel representation learning framework
that captures geometric information of the scene, such as distance or shape.
[PDF]
[Code]
|
|
Robust Imitation via Mirror Descent Inverse Reinforcement Learning
Dong-Sig Han, Hyunseo Kim, Hyundo Lee, JeHwan Ryu, Byoung-Tak Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2022
Inspired by a first-order optimization method called mirror descent, this paper proposes to predict a sequence of reward functions, which are iterative solutions for a constrained convex problem.
[PDF]
[Code]
|
|
Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
Taehyeong Kim, Injune Hwang, Hyundo Lee, Hyunseo Kim, Won-Seok Choi, Joseph J Lim, Byoung-Tak Zhang
International Conference on Machine Learning (ICML), 2021
We propose Message Passing Adaptive Resonance Theory (MPART) that learns the distribution and topology of input data online. Through message passing on the topological graph, MPART actively queries informative and representative samples, and continuously improves the classification performance using both labeled and unlabeled data.
[PDF]
|
|
Visual Perception Framework for an Intelligent Mobile Robot
Chung-Yeon Lee, Hyundo Lee, Injune Hwang, Byoung-Tak Zhang
17th International Conference on Ubiquitous Robots (UR), 2020
We present a visual perception framework for an intelligent mobile robot. Based on the robot operating system middleware, our framework integrates a broad set of advanced algorithms capable of recognising people, objects and human poses, as well as describing observed scenes.
[PDF]
|
|
Spatial Perception by Object-Aware Visual Scene Representation
Chung-Yeon Lee, Hyundo Lee, Injune Hwang, Byoung-Tak Zhang
ICCV Workshop on Deep Learning for Visual SLAM, 2019
We present a spatial perception framework that uses an object-aware visual scene representation to enhance the spatial abilities. The proposed representation compensates for aberrations of conventional geometric scene representations by fusing those representations with semantic features extracted from perceived objects.
[PDF]
|
|
Encoder-Powered Generative Adversarial Networks
Jiseob Kim, Seungjae Jung, Hyundo Lee, Byoung-Tak Zhang
arXiv, 2019
We present an encoder-powered generative adversarial network (EncGAN) that is able to learn both the multi-manifold structure and the abstract features of data.
[PDF]
|
The source of this website is from here.
|
|