Taehoon Kim
About
Hi! I am a 3rd year MS/PhD integrated student at SNU Computer Vision Lab, advised by Bohyung Han. My primary research interest lies in the development of deep learning models that exhibit robust behavior in scenarios where distributional challenges are prevalent, e.g. Continual Learning and Domain Generalizaton. Currently, I am interested in reliable and controllable generative models.
Education
-MS/Ph.D. Electrical and Computer Engineering, Seoul National University
Mar, 2022 ~ Current
Advisor: Bohyung Han
-B.S. Mathematical Science & Computational Science, Seoul National University
Mar, 2016 ~ Feb, 2022
Publications
Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
Taehoon Kim, Donghwan Jang, Bohyung Han
CLVision Workshop, CVPR2024
[paper]
Cross-Class Feature Augmentation for Class Incremental Learning
Taehoon Kim, Jaeyoo Park, Bohyung Han
AAAI2024,
CLVision Workshop, CVPR2024
[arxiv]
Randomized Adversarial Perturbations for Domain Generalization
Taehoon Kim, Bohyung Han
WACV2024
[arxiv]
Services
Teaching Assistant
Principles of Computer vision, SNU M2608.001900, Prof. Bohyung Han, Spring 2023
FCOS, Samsung Electronics, Feb 2022
Academic Review
ICLR, TPAMI