Scholar
Sanghyun Jo
Google Scholar ID: xgP6q2YAAAAJ
OGQ · SNU AIBL Lab
Citations & Impact
Citations
221
H-index
4
i10-index
3
Publications
11
Co-authors
9
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - [ICIP 2021] Puzzle-CAM: Improved localization via matching partial and full features.
- - [Under Review] RecurSeed and EdgePredictMix: Single-stage learning is sufficient for Weakly-Supervised Semantic Segmentation.
- - [ICCV 2023] MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation.
- - [ECCV 2024] DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class.
Research Experience
- - AI Researcher at OGQ
- - Involved in multiple research projects including PuzzleCAM, RecurSeed_and_EdgePredictMix, MARS, and DHR.
Education
- SNU AIBL Lab, advised by Prof. Kyungsu Kim.
Background
- Building interpretable, label-efficient, and multimodal AI systems. Currently an AI Researcher at OGQ.
Miscellany
- Active on GitHub with 73 repositories and 62 stars.
