Junghyun Lee
Junghyun Lee
Home
Experiences
Publications
Projects
Posts
Seminars
Organizer
Korean AI Theory Community Workshop
SNU-KAIST ML/AI Theory Workshop
Machine/Deep Learning Theory + Physics Seminar
Contact
Light
Dark
Automatic
Active Learning
Querying Easily Flip-flopped Samples for Deep Active Learning
Proposes a new active learning approach by proposing a new uncertainty measure called the least disagree metric, as well as its efficient estimator, which is proven to be asymptotically consistent. This is then combined with seeding to become a new active learning algorith, LDM-S, which is shown to outperform existing approaches across various architectures and datasets.
Seong Jin Cho
,
Gwangsu Kim
,
Junghyun Lee
,
Jinwoo Shin
,
Chang D. Yoo
PDF
Cite
Project
Least Disagreement-based Active Learning
A new disagreement-based approach to active classification and regression.
Junghyun Lee
Cite
×