1 code implementation • 10 May 2024 • Joonho Lee, Jae Oh Woo, Juree Seok, Parisa Hassanzadeh, Wooseok Jang, JuYoun Son, Sima Didari, Baruch Gutow, Heng Hao, Hankyu Moon, WenJun Hu, Yeong-Dae Kwon, TaeHee Lee, Seungjai Min
Assessing response quality to instructions in language models is vital but challenging due to the complexity of human language across different contexts.
no code implementations • ICCV 2023 • Joonho Lee, Jae Oh Woo, Hankyu Moon, Kwonho Lee
Deploying deep visual models can lead to performance drops due to the discrepancies between source and target distributions.
no code implementations • 8 Aug 2022 • Ayaan Haque, Hankyu Moon, Heng Hao, Sima Didari, Jae Oh Woo, Patrick Bangert
3D deep learning is a growing field of interest due to the vast amount of information stored in 3D formats.
no code implementations • 24 Jan 2022 • Jae Oh Woo
Mutual information is an example of an uncertainty measure in a Bayesian neural network to quantify epistemic uncertainty.
no code implementations • 16 Jun 2021 • Hankyu Moon, Heng Hao, Sima Didari, Jae Oh Woo, Patrick Bangert
Key to this approach is the pattern space, a latent space of patterns that represents all possible sub-images of the given image data.
1 code implementation • 30 May 2021 • Jae Oh Woo
The info-max learning principle maximizing mutual information such as BALD has been successful and widely adapted in various active learning applications.
no code implementations • 25 Feb 2021 • Heng Hao, Hankyu Moon, Sima Didari, Jae Oh Woo, Patrick Bangert
We propose a highly data-efficient active learning framework for image classification.