Scholar
Hyounguk Shon
Google Scholar ID: KZSXUmsAAAAJ
KAIST
Citations & Impact
Citations
230
H-index
5
i10-index
4
Publications
12
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- WACV: SFLD: Reducing the content bias for AI-generated Image Detection
- IJCAI Workshop: Neural Vicinal Risk Minimization: Noise-robust Distillation for Noisy Labels
- AAAI: FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
- ICCV: Disposable Transfer Learning for Selective Source Task Unlearning
- ECCV: DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning
- CVPR: Joint Negative and Positive Learning for Noisy Labels
- NeurIPS: UniCLIP: Unified Framework for Contrastive Language-Image Pre-training
- ICRA: Lightweight Monocular Depth Estimation via Token-Sharing Transformer
- ECCV: On the Angular Update and Hyperparameter Tuning of a Scale-Invariant Network
Research Experience
- Former research intern at LG AI Research, mentored by Dr. Janghyeon Lee.
Education
- PhD student at KAIST SIIT Lab, supervised by Prof. Junmo Kim and also advised by Prof. Yunho Jeon.
Background
- Research interests include machine learning, deep learning, and computer vision. Recent works involve continual learning and unlearning, noisy label learning, multi-modal contrastive learning, and scalable hyperparameter search.
