Jaehyeok Bae

Hello! I am currently applying for graduate studies in 2024. I look forward to collaborate with professionals in the global research community, including both academia and industry.

I received my Bachelor's science (Summa Cum Laude) in Electrical and Computer Engineering at Seoul National University, where I was supported by Presidential Science Scholarship. Previously, I spent spent some time at Gauss Labs as a computer vision applied scientist intern.

Email  /  CV  /  Scholar  /  LinkedIn  /  Github

Research

I'm interested in computer vision, machine learning, image processing, along with biomedical imaging.

Specifically, my goal is to develop CV/ML applications for medical and industrial domains, alongside future medical devices, thereby significantly contributing to patient care, diagnosis, and treatment.

* denotes equal contribution.

- Proposed a novel anomaly detection and localization alogrithm for industrial datasets, by training a normal feature distribution using position and neighborhood information of local features.

- Introduced N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras.

- Empirically showed that pretraining on N-ImageNet improves the performance of event-based classifiers.

- Proposed a design method for a perforated panel to reduce the level of incident noise without obstructing the flow of incoming fluid. (written in Korean)

Project

- Proposed an algorithm to restore aliased images from accelerated MRI scans into aliasing-free images, 2nd place award in the 2022 competiton.

- Served as the contest coordinator for the 2023 competition, evaluating and analyzing the participants' models.

Check out Jon Barron's repository for the template of this website.