About me

I am Yoojin Oh, an undergraduate student majoring in Artificial Intelligence at Ewha Womans University. I am currently a research intern at the Computer Vision Lab and previously worked at the Practical AI LAB. My research interests include: (i) Generative Models, (ii) Weakly/Self-Supervised Learning, (iii) Multi-modal Learning. If you are interested in my work or would like to connect, please feel free to reach out via email.

News

Jul. 2025: Our work Beyond Softmax was accepted to BMVC 2025.
Jun. 2025: Our work SteeringTTA was accepted to ICML PUT Workshop 2025.

Education

B.S. in Ewha Woman’s University (2022~present)
- Major in Artificial Inteligence
Sookmyung Woman’s High School, Seoul (2018~2022)

Research Experience

Computer Vision Lab (2025.6 ~ present)
- Advisor : Suha Kwak
- Audio-Visual Multi-modal Learning
PAI Lab (2024.3 ~ 2025.6)
- Advisor : Junhyug Noh
- Robust Learning tasks using Diffusion models.
- Weakly-Supervised-Object-Localization (WSOL) tasks.
AIsec Lab (2023.12 ~ 2024.2)
- Advisor : Seeun Oh
- Advancing data augmentation of network traces for self-supervised learning in Realistic Website Fingerprinting and information leakage estimation based on WeFDE framework.

Publications

Yoojin Oh, Junhyug Noh. “Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps.”, BMVC 2025.
Jihyun Yu, Yoojin Oh, Wonho Bae, Mingyu Kim, Junhyug Noh. “SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation.” ICML PUT Workshop 2025

Work Experience

Spresto (2024.7 ~ 2025.5)

Research Intern
Develop a Spycam detection model to prevent illegal filming.

Naver Z (2023.7 ~ 2023.8)

Fine-tune Stable diffusion & Create LoRA for ZEP object generation
Advancing Chatbots based on Prompt Engineering techniques.

Contact

E-Mail : mydianaoh@ewha.ac.kr / dianaoh1021@gmail.com