Jongoh Jeong

Jongoh Jeong
jeong2 [at] kaist.ac.kr / [CV] [Google Scholar] [Github] [LinkedIn]

🔍 About Me

My name is Jongoh Jeong, a Robotics Ph.D. degree candidate at the Korea Advanced Institute of Science and Technology (KAIST), South Korea, where I am advised by Prof. Kuk-Jin Yoon at Visual Intelligence Lab. My research spans from data-efficient visual representation learning to robust domain adaptation/generalization in order to design effective visual learning algorithms for efficient data use with minimal human supervision.

🎓 Education

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea

🏫 Ph.D. Candidate in Robotics (Advisor: Prof. Kuk-Jin Yoon), 2022 - Present
🎓 M.S. in Electrical Engineering (Advisor: Prof. Jong-Hwan Kim), 2020 - 2022

The Cooper Union for the Advancement of Science and Art, New York, NY, USA

🎓 B.Eng. in Electrical Engineering, 2014 - 2020

📖 Publications (W: Workshop, C: Conference, J: Journal)

Interests: Data-efficient visual representation learning, latent space manipulation, domain adaptation/generalization, continual learning, autonomous driving

[C4] Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks

Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon
European Conference on Computer Vision (ECCV), Sep. 2024.

[Paper]

[C3] FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks

Hunmin Yang*, Jongoh Jeong*, Kuk-Jin Yoon (*Equal contribution)
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), Feb. 2024.
*Extension of [W2]

[Paper]

[C2] Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint Prediction

Hwan-Soo Choi*, Jongoh Jeong*, Young Hoo Cho, Kuk-Jin Yoon, Jong-Hwan Kim. (*Equal contribution)
Robot Intelligence Technology and Applications (RiTA), Dec. 2023.

[Paper]

[W2] FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks

Hunmin Yang*, Jongoh Jeong*, Kuk-Jin Yoon (*Equal contribution)
ICCV 2023 Workshop on Adversarial Robustness In the Real World (AROW 2023)
[Extended Abstract]

[J2] Adaptive Bayesian Optimization for Fast Exploration Under Safety Constraints

Guk Han, Jongoh Jeong and Jong-Hwan Kim.
IEEE Access. Apr. 2023.

[Paper]

[C1] Doubly Contrastive End-to-End Semantic Segmentation for Autonomous Driving under Adverse Weather

Jongoh Jeong and Jong-Hwan Kim.
British Machine Vision Conference (BMVC), Nov. 2022.

[Paper][Project]

[J1] End-to-end Real-time Obstacle Detection Network for Safe Self-driving via Multi-task Learning

Taek-Jin Song*, Jongoh Jeong* and Jong-Hwan Kim. (*Equal contribution)
IEEE Transactions on Intelligent Transportation Systems (IEEE T-ITS), Sept. 2022.

[Paper] [Project]

[W1] Using Privileged Information to Improve Prediction in Health Data: A Case Study.

Jongoh Jeong, Do Hyung Kwon, Min Joon So, Anita Raja, Shivani Ghatge, Nicolae Lari and Ansaf Salleb Aouissi.
NeurIPS 2019 Workshop on Information Theory and Machine Learning (ITML 2019)

[Paper]

🗂️ Research Projects

AI/SW Project for Commissioned Education (Ministry of National Defense (MND), Jul.'22 – Dec.'26)
Synthetic Military Target Data Generation for Domain Adaptive Object Detection (LIGNex1, Oct.’22 – Sep.’23)
Development of Artificial Intelligence Technology that Continuously Improves Itself as the Situation Changes in the Real World
(Korea MSIT (IITP), No.2020-0-00440, Sep.’20 –Aug.’22)
Development of Real-time Smart Solution for Solder Mount Technology (SMT) (Koh-Young Tech., Sep.’20 – Aug.’22)

📤 Academic Activities

Reviewer

IEEE Transactions on Geoscience and Remote Sensing (T-GRS), 2024-Present
- IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2022-Present
IEEE Access, 2022-Present
NeurIPS Workshop on Machine Learning for Health (ML4H), 2020-Present

Professional Society Membership

- Order of the Engineer 2020 – Present
- IEEE-Eta Kappa Nu, Student Member 2018 – Present
- ACM, Student Member 2018 – Present