Interests : Computer Vision, Deep learning, Data Scientist & Engineering

Reach Out

+82 1039993403

Seoul, Korea

[email protected]

[https://github.com/pcmin03](https://smoggy-fibula-4b3.notion.site/https-github-com-pcmin03-9b6ce78ae7754ab79fa85d7ff09e4b0d)

[https://stickypanda.tistory.com/](https://smoggy-fibula-4b3.notion.site/https-stickypanda-tistory-com-0e752596527e4a94a3d093beebfd88f7)


Skill Set

2D/3D Image Detection

Semi-Supervised Learning

Domain Adaptation

Image Segmentation

Evaluation Metric


Personal Study

Pseudo Lab

Book reviewer

Research Field


Honors & Awards

Awards

Tools

Skills

✋ About Me

document.pdf

I am currently working as a Medical Image Processing Researcher at POSCODX I am involved in researching and developing deep learning applications for various domains (ex: Medica & Industry).

I enjoy the process of understanding unfamiliar concepts and acquiring new knowledge, and it brings me great joy. 😆

I always approach learning with humility, seeking knowledge from others when I don't know something and gladly sharing what I know with others.

Pride brings a person low, but the lowly in spirit gain honor. Proverbs 29:23

Work Experience

💻 AI Research Engineer July 2024 - Present

Pangyoyeok, Korea , POSCO DX

💻 Data Scientist May 2021 - July 2024

Seoul, Korea , VUNO.inc

Technical application of 2D/3D detection in the Medical Domain (Pathology, CT, MRI). Development of a KFDA-certified Deep Learning Algorithm for Quantitative Analysis of Ki-67 through actual productization.Experience in maintenance using various ops such as CI/CD, Docker, etc.

🧑‍🏫 Part-Time Lecturer oct 2023 - Jul 2023

Seoul, Korea , FastCampus

Conducting lectures on the overall field of computer vision. Hands-on practice with end-to-end learning through various projects. Detailed review of technical papers.

Paper List

H., Park, C., Kim, D. H., Kim, J., & Kim, W. H. (2024). CNG-SFDA: Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation. In Proceedings of the Asian Conference on Computer Vision (pp. 1723-1740).506a3bProjects (Paper link)

Kim, D. H., Cho, S., Cho, H., Park, C., Kim, J., & Kim, W. H. (2024). Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture. arXiv preprint arXiv:2407.10733. (paper link)

Park, C. QUANTITY OR CERTAINTY: CAN AMBIGUOUSLY ANNOTATED DATA IMPROVE LUNG NODULE DETECTION PERFORMANCE? RSNA: Radiological Society of North America

Park, C., Lee, K., Kim, S. Y., Cecen, F. S. C., Kwon, S. K., & Jeong, W. K. (2021, April). Neuron segmentation using incomplete and noisy labels via adaptive learning with structure priors. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) (pp. 1466-1470). IEEE. (paper link)

My Project