Search Results for author: Jongmok Kim

Found 4 papers, 2 papers with code

Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation

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).

Pose Estimation Semi-Supervised Human Pose Estimation

Paper
Add Code

MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection

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.

Data Augmentation object-detection +2

Paper
Code

MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection

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.

Ranked #4 on Semi-Supervised Object Detection on COCO 0.5% labeled data

Data Augmentation object-detection +2

Paper
Code

Structured Consistency Loss for semi-supervised semantic segmentation

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.

General Classification Segmentation +1

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.