← Search

Hyeonsu Jeong

2 accepted papers

2025

Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels

ICLR 2025poster

We investigate the mechanisms of self-distillation in multi-class classification, particularly in the context of linear probing with fixed feature extractors where traditional feature learning explanations do not apply. Our theoretical analysis reveals that multi-round self-distillation effectively…

Cited by 0SourcePDFScholar
2023

Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing

ICML 2023poster

Crowdsourcing has emerged as an effective platform for labeling large amounts of data in a cost- and time-efficient manner. Most previous work has focused on designing an efficient algorithm to recover only the ground-truth labels of the data. In this paper, we consider multi-choice crowdsourcing ta…