no code implementations • 15 Mar 2022 • Jongmok Kim, Hwijun Lee, Jaeseung Lim, Jongkeun Na, Nojun Kwak, Jin Young Choi
A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL).
1 code implementation • CVPR 2022 • Jongmok Kim, Jooyoung Jang, Seunghyeon Seo, Jisoo Jeong, Jongkeun Na, Nojun Kwak
Data augmentation strategy plays a significant role in the SSL framework since it is hard to create a weak-strong augmented input pair without losing label information.
1 code implementation • 22 Nov 2021 • Jongmok Kim, Jooyoung Jang, Seunghyeon Seo, Jisoo Jeong, Jongkeun Na, Nojun Kwak
Data augmentation strategy plays a significant role in the SSL framework since it is hard to create a weak-strong augmented input pair without losing label information.
no code implementations • 14 Jan 2020 • Jongmok Kim, Jooyoung Jang, Hyunwoo Park, Seongah Jeong
We propose a structured consistency loss to address this limitation of extant studies.