About Me
Resume - JunHa Song
This blog will be removed soon. Please visit my new blog.
I’m Junha Song (CV), a second-year MS.D student at KAIST, advised by Prof. In So Kweon. I was a research engineer at HYUNDAI MOBIS (virtual) in 2021 and a research intern at Qualcomm (virtual) in 2022-2023. Please visit my Git-blog for my research note from which you can see that I am a highly self- motivated student. My research interest lies in the intersection of machine learning and computer vision. I always dream that my research can help many people someday.
Junha Song
- Curriculum Vitae (CV)
- Email : sb020518@kaist.ac.kr
- Git Blog : https://junha1125.github.io
- M.S Candidate of KAIST RCV Lab under Prof. In So Kweon
Research Experiences
- July 2022 - present
Qualcomm (virtual)
Research Intern
Mentors: Sungha Choi - March 2021 - June 2022
HYUNDAI MOBIS (virtual)
Research Engineer - (ECCV 2022 Submitted) J Song, K Pack, I Shin, S Woo, C Zang, I Kweon. “CD-TTA: Compound Domain Test Time Adaptation for Semantic Segmentation”
Education
- 2021 ~ present
KAIST - Division of Future Vehicle
RCV Lab under Prof. In So Kweon
M.S. Candidate - 2015 ~ 2020
Kookmin University (Seoul, Korea)
Department of Automobile and IT Convergence
B.S.
Official Grade
- B.S Credit
4.39 / 4.5 (Percent: 98.7/100 | Rank: 2/121 | Major: 4.43) - TOEIC
2018.08 - 880 / 990
2020.08 - 825 / 990 - OPIC
2020.07 - IH (Intermediate High) - TOEIC SPEAKING
2022.01 - 150 (Lv6)
Research Interests
- Test-time Adaptation (on-device learning)
- Self-supervised learning (representation learning)
- Domain Generalization
- Reducing the efforts of the human annotator with domain adaptation or active learning
- But not limited to.
Awards and Honors
- Vehicle monitoring over internet toward digital twins, Honorable Judge Award (Future Transport Design Award), Cloud Programming World Cup, Japan (2019)
- Capstone Awards, The Korean Society of Automotive Engineers, Korea (2019)
- National Science and Engineering Scholarship (Full Tuition), Korea Scholarship Foundation (2018 ~ 2020)
- Fast Campus, lecture planning consultant (2022)
Projects
- Detection of Surrounding Vehicles using Deep Neural Network and Fusion of Panoramic Camera and Lidar Sensor, KOFAC(한국과학창의재단), Korea (2019)
- Satellite image precision object detection, DACON(국방과학연구소), Korea (2020)
- Development of robust segmentation network having environment invariance, HYUNDAI MOBIS(현대모비스), Korea (2021)
- Development of real-time masking/unmasking system for personal video information for public services such as CCTV (CCTV 등 공공서비스용 개인영상정보 실시간 마스킹/언마스킹 시스템 개발, News1), Ministry of Science and ICT(과학기술정보통신부), Korea (2021~)
B.S. Research Experiences
- Research Intern at Intelligence and Interaction Lab, Kookmin University (Feb. 2019 ~ Nov. 2019)
- Research Intern at Machine Intelligence Lab, Kookmin University (Dec. 2019 ~ Present)
- Junha Song, et al, “센서 퓨전과 통신을 이용한 차량의 디지털 트윈의 구현”, The Korean Sociey of Automotive Engineers, Korea (2019)
- Myunghak Lee, Junha Song, “Style Transfer Maps from Satellite Images by using Generative Models”, KICS, Korea (2020)
Skills
- Programming language: Python, C++
- Machine Learning Librarie: Pytorch, Tensorflow
- Application development: ROS (Robot Operating System)
- Sensor utilization: Camera, RGB-D Camera, LIDAR, GPS/IMU