Junsu Kim
t=480
CVPR 2024 Highlight Poster

Presenting diffusion-based replay research for class-incremental object detection.

Current Base UNIST Busan Centum Campus
click to denoise
AI Researcher at UNIST AIGS

Junsu Kim

Combined MS-PhD student building open-world perception systems across computer vision, continual learning, and foundation models.

Continual Learning Open-world Detection Vision-Language Models Diffusion Models

I am a Combined MS/PhD student at UNIST AIGS, advised by Prof. Seungryul Baek, with research interests in continual learning, open-world detection, and vision-language systems.

Previously, I interned at NAVER AI Lab advised by Dongyoon Han, where I studied backbone architectures and analyzed internal representations of large-scale models. I also serve as an NVIDIA AI Ambassador, driven by a passion for applying AI to real-world, everyday problems.

Email Scholar GitHub LinkedIn Blog CV
New Selected as an Outstanding Reviewer at BMVC 2025
New Jul 2025 · One paper accepted to BMVC (co-first author)
New Jul 2025 · Two papers accepted to ICCV Workshops (1st author)
Highlight CVPR 2024 first-author paper selected as Highlight Poster (top 2.8%)
Open to Opportunities Actively Searching AI Research Internships I am actively seeking AI research internship opportunities where I can work on practical research in industry, especially around 2D/3D representation, continual learning, and large-scale vision-language or diffusion models.
Contact Me

Publications

0+ Total Citations

Showing 7 papers (+6 domestic)

BMVC 2025 2025
B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing
J. Kim*, Y. Jang*, H. Kim, E. Lee, E. Kim, S. Baek, J. Yoo
Paper Summary
B-RIGHT Figure
A systematic re-evaluation of existing HOI benchmarks, revealing integrity issues and proposing new evaluation protocols for generalized human-object interaction testing.
ICCV-W 2025 2025
Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning
J. Kim, Y. Ku, S. Baek
Paper Summary
FSCIL Synthetic Figure
Investigates whether synthetic image generation can effectively address catastrophic forgetting in few-shot class-incremental learning, challenging common assumptions in the field.
ICCV-W 2025 2025
Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark
J. Kim, N. Kim, J. Lee, I. Park, D. Han, S. Baek
Paper Code Summary
RPE Figure
Critically examines the reliability of reasoning-based pose estimation benchmarks, identifying systematic biases and proposing refined evaluation metrics.
ArXiv 2025 2025
Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge
J. Kim, Y. Ku, D. Han, S. Baek
Paper Summary
Diffusion FSCIL Figure
Bridges diffusion models with few-shot class incremental learning, leveraging generative priors to overcome data scarcity and catastrophic forgetting simultaneously.
CVPR Highlight · Top 2.8%
CVPR 2024 · Highlight 2024
SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection
J. Kim, H. Cho, J. Kim, Y. Tiruneh, S. Baek
Paper Summary
SDDGR Figure
Proposes using Stable Diffusion as a generative replay mechanism for class incremental object detection, effectively mitigating catastrophic forgetting while maintaining high-quality synthetic data generation.
CVPR-W 2024 2024
VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection with Vision-Language Model
J. Kim, Y. Ku, J. Kim, J. Cha, S. Baek
Paper Summary
VLM-PL Figure
Leverages vision-language models for advanced pseudo labeling in class incremental object detection, improving detection accuracy on novel classes without forgetting.
ICASSP 2024 2024
Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy
J. Kim, S. Hong, C. Kim, J. Kim, Y. Tiruneh, J. On, J. Song, S. Choi, S. Baek
Paper Summary
ICASSP Figure
Introduces a class-wise buffer management strategy for incremental object detection that optimizes exemplar selection and training to balance old and new class performance.
IEIE Summer 2023 2023
Reducing Data Imbalance for Object Detection
J. Kim, S. Hong, C. Kim, J. Kim, J. On, Y. Tiruneh, J. Song, S. Choi, S. Baek
JKAIA 2022 2022
Temporal MANO-Based Video Hand Pose and Shape Estimation
H. Park, J. Kim, J. Kim, S. Baek
Best Paper Award
IEIE Fall 2021 2021
Multi-Task Learning Approach to Autonomous Driving Techniques
I. Lee, J. Kim, H. Lee, Y. Kim, D. Lee, H. Lee
Best Paper Award
KICS Summer 2021 2021
Deep Learning-Based Self-Driving Systems for Swarm Vehicles
H. Kim, J. Kim, I. Lee, H. Lee
Best Paper Award
IEMEK ICT 2021 2021
AI Edge Server Design for Swarm Vehicular Networks
J. Kim, H. Kim, I. Lee, H. Lee
KICS Winter 2021 2021
AI-Enabled Low-Complexity Autonomous Driving Using TensorRT
H. Kim, J. Kim, I. Lee, H. Lee

Education

2023 – Present
Combined MS-PhD in AI
UNIST, Ulsan, South Korea
Advisor: Prof. Seungryul Baek
2016 – 2022
B.S. in Information and Communications Engineering
Pukyong National University, Busan
Research advised by Prof. Hoon Lee since 2019

Experience

2024 – 2025
AI Research Intern
NAVER AI Lab, Seoul
Backbone Research Team · Advisor: Dongyoon Han
2022 – 2025
NVIDIA AI Ambassador
NVIDIA DLI Program
Leader, NVIDIA · MODULABS Foundation Models Lab
2022 – 2023
AI Research Intern
UVL Lab, Ulsan & Corp. KST, Busan

Awards

2025 Outstanding Reviewer, BMVC 2025
2025 Excellence Award, 37th IPIU Poster Presentation
2021 Best Paper Award, IEMEK · KICS · IEIE
2021 1st Prize, PKNU Capstone Design
2020 2nd Prize, Busan AI Idea Contest (기술보증기금)

Honored To

2025 Serve as reviewer for AAAI, BMVC (Outstanding), IEEE TMM, IEEE TIP
2025 Be invited as Young Researcher to National Physical-AI Strategy Advisory Seminar (Invited by ETRI)
2024 Present oral talk at KOREA Digital Innovators Symposium as UNIST representative
2024 Present poster at KCCV 2024

Teaching & Mentoring

Samsung SSAFY (13th)

Lecture Mentor · Language Models & RAG, Jul 2025

UNIST AI Novatus Academia

Workshop Lecturer · Computer Vision, 2023

NVIDIA Jetson AI Workshop

Pukyong National University, May 2022

"Shoot for the moon. Even if you miss, you'll land among the stars."

Norman Vincent Peale

NVIDIA AI Ambassador