Hello, I study machine learning and computer vision.
My research goal is to design machines to learn and understand the world like humans.
It leads me to think about follow-up researches: 1. Data- and Label-efficient learning 2. Learning from noisy labels 3. Depth estimation and 3D scene understanding
News
- (07/2022) Our paper accepted at ECCV 2022.
- (06/2020) Our paper accepted at CVPR 2020 workshop.
- (06/2020) Our team won 1st and 2nd place in WSOL and WSSS at LID challenge.
- (07/2019) Our paper accepted at ICCV 2019.
Publications
Object Discovery via Contrastive Learning for Weakly Supervised Object Detection.
Jinhwan Seo, Wonho Bae, Danica J. Sutherland, Junhyug Noh*, Daijin Kim*
ECCV 2022 - paper | project page | code
Revisiting Class Activation Mapping for Learning from Imperfect Data.
Wonho Bae*, Junhyug Noh*, Jinhwan Seo, Gunhee Kim
CVPRW 2020 - paper
Better to Follow, Follow to be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object Detection.
Junhyug Noh, Wonho Bae, Wonhee Lee, Jinhwan Seo, Gunhee Kim
ICCV 2019 - paper
Awards
- Winner of LID Challenge - WSOL (1st) and WSSS (2nd)