no code implementations • CVPR 2023 • Jongin Lim, Youngdong Kim, Byungjai Kim, Chanho Ahn, Jinwoo Shin, Eunho Yang, Seungju Han
Our key idea is that an adversarial attack on a biased model that makes decisions based on spurious correlations may generate synthetic bias-conflicting samples, which can then be used as augmented training data for learning a debiased model.
no code implementations • 2 May 2021 • Byungjai Kim, Kinam Kwon, Changheun Oh, HyunWook Park
The feature is collaboratively used with another feature that is the low-dimensional representation of multi-contrast images.
1 code implementation • 17 Mar 2020 • Sunho Kim, Byungjai Kim, HyunWook Park
Deep neural networks are trained by learning data.
no code implementations • 19 Oct 2019 • Jee Won Kim, Kinam Kwon, Byungjai Kim, HyunWook Park
In this paper, we observed that in a real MRI environment, two distorted images obtained with opposite polarities of readout gradient showed artifacts in a different region.