← Search

Gyoomin Lee

2 accepted papers

2025

DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation

NeurIPS 2025poster

Source-free domain adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain without requiring labeled source data. In a self supervised setting, relying on pseudo labels on target domain samples facilitates the domain adaptation performance providing strong supervisi…

Cited by 0SourcecodeScholar
2024

Not All Classes Stand on Same Embeddings: Calibrating a Semantic Distance with Metric Tensor

CVPR 2024poster

The consistency training (CT)-based semi-supervised learning (SSL) bites state-of-the-art performance on SSL-based image classification. However the existing CT-based SSL methods do not highlight the non-Euclidean characteristics and class-wise varieties of embedding spaces in an SSL model thus they…

Cited by 3SourcePDFScholar