Youngwook Kim
I am an Assistant Professor at School of Artificial Intelligence, College of Computer Science, Kookmin University.
I received my Ph.D degree from Department of Eletrical and Computer Engineering, Seoul National University, in 2024, under advisor Jungwoo Lee. Also, I received my bachelor's degree from Department of Civil and Environmental Engineering, Seoul National University, in 2018.
Email  / 
Google Scholar  / 
Github  / 
Linkedin  / 
Resume
|
|
News
AI VISION Lab (Applied & Intelligent VISION Lab) (https://aivision.kookmin.ac.kr/) μμ ν¨κ» μ°κ΅¬ν λνμμμ λͺ¨μ§ν©λλ€. κ΄μ¬μμΌμ λΆμ μ΄λ©μΌλ‘ λ¬Έμ λ°λλλ€.
|
Research
I'm interested in computer vision, learning from noisy labels, multi-label learning, weakly supervised learning, and remote sensing.
|
|
A Plug-In Curriculum Scheduler for Improved Deformable Medical Image Registration
Jiyoon Shin, Youngwook Kim, Jungwoo Lee
IEEE Access, 2025
We propose an automated curriculum learning solution for medical image registration that does not require expert knowledge or prior experience.
|
|
Learning Dual Hierarchical Representation for 3D Surface Reconstruction
Jiyoon Shin, Youngwook Kim, Sangwoo Hong, Jungwoo Lee
Asian Conference on Computer Vision (ACCV), 2024
We introduce Dual Hierarchical Representation (DHR), which allows for faithful reconstructions under constrained computation.
|
|
Instance-Dependent Multi-Label Noise Generation for Multi-Label Remote Sensing Image Classification
Youngwook Kim, Sehwan Kim, Youngmin Ro, Jungwoo Lee
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2024
[GitHub]
We introduce generating instance-dependent multi-label noise into multi-label remote sensing image datasets which is more feasible and challenging noise scenario.
|
|
Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification
Youngwook Kim, Jae Myung Kim, Jieun Jeong, Cordelia Schmid, Zeynep Akata, Jungwoo Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[GitHub] /
[arXiv] /
[Project page] /
[Poster] /
[Slide] /
[YouTube]
By investigating the difference in model explanation, we devise a simple but effective solution to compensate the damage by false negative labels.
|
|
Large Loss Matters in Weakly Supervised Multi-Label Classification
Youngwook Kim*, Jae Myung Kim*, Zeynep Akata, Jungwoo Lee
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[GitHub] /
[arXiv] /
[Poster] /
[Slide]
By utilizing memorization effect, we can efficiently train multi-label classification model with small number of partially annotated labels.
|
Invited Talk
|
Smart city seminar, Seoul National University, Department of Civil and Environmental Engineering, September 2023
AIIS Spring retreat (Oral presenation), May 2023 [Presentation video] (in Korean)
University of Seoul, June 2022
Kakao enterprise, July 2022
|
Teaching
|
Artificial Intelligence, Fall 2024
Intelligent Mobility Services, Fall 2024
Multimodal Artificial Intelligence, Spring 2025
Recent topics in Artificial Intelligence, Spring 2025
Multidisciplinary Capstone Project, Spring 2025
|
Reviewer Service
|
Conferences : CVPR, ICCV, ECCV
Journals : IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Multimedia (TMM)
|
The format of this website is borrowed from Jon Barron.
|
|