← Search

Sunguk Jang

2 accepted papers

2026

SCAD: Super-Class-Aware Debiasing for Long-Tailed Semi-Supervised Learning

ICLR 2026poster

In long-tailed semi-supervised learning (LTSSL), pseudolabeling often creates a vicious cycle of bias amplification, a problem that recent state-of-the-art methods attempt to mitigate using logit adjustment (LA). However, their adjustment schemes, inherited from LA, remain inherently hierarchyagnost…

Cited by 0SourcecodeScholar
2023

Decoupled Training for Long-Tailed Classification With Stochastic Representations

ICLR 2023poster

Decoupling representation learning and classifier learning has been shown to be effective in classification with long-tailed data. There are two main ingredients in constructing a decoupled learning scheme; 1) how to train the feature extractor for representation learning so that it provides general…

Cited by 17SourcePDFScholar