Jin-Seop Lee

I am a Ph.D. candidate in the Information & Intelligence System Lab (IISLab) at Sungkyunkwan University, supervised by Prof. Jee-Hyong Lee. I received my Bachelor's degree from Sungkyunkwan University.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github

Research

My research interests include various tasks in computer vision, multi-modal learning, deep learning, and machine learning. I have been conducted research on data-efficient learning methods, including self-/semi-supervised learning, weakly-supervised learning, and domain generalization. Furthermore, I am currently interested in efficient reasoning model, multi-modal learning, and video understanding/synthesis.

DCG-SQL improves text-to-SQL generation by incorporating a deep contextual schema link graph that captures key elements and semantic relationships between the question and database schema.

DomCLP enhances generalization to unseen domains by combining domain-aware contrastive learning with prototype mixup to learn robust and domain-invariant features.

FSAE improves weakly-supervised segmentation by expanding Class Activation Maps along feature and spatial dimensions to better capture full object regions.

IGNORE identifies and filters hidden positive labels using information gaps from pseudo masks to reduce false negatives in single-positive multi-label learning.

ExMatch boosts semi-supervised learning with extremely limited labels by selectively leveraging confident unlabeled samples for self-training.

LSL improves noisy label learning by incorporating structural information from data distribution to prevent overfitting to incorrect labels.

Our zigzag process automates trimming die inspection through alternating AI and CAD collaboration, achieving high accuracy and significantly reduced inspection time.

Our method achieves robust defect classification in semiconductor manufacturing by combining localization-guided detection with semi-supervised learning.

Education

Design and source code from Jon Barron's website.