← Search

Sui Jiet Tay

2 accepted papers

2025

Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL

ICML 2025poster

Modern semi-supervised learning (SSL) methods rely on pseudolabeling and consistency regularization. Pseudolabeling is typically performed by comparing the model's confidence scores and a predefined threshold. While several heuristics have been proposed to improve threshold selection, the underlyin…

Cited by 0SourcePDFScholar
2024

Pearls from Pebbles: Improved Confidence Functions for Auto-labeling

NeurIPS 2024poster

Auto-labeling is an important family of techniques that produce labeled training sets with minimum manual annotation. A prominent variant, threshold-based auto-labeling (TBAL), works by finding thresholds on a model's confidence scores above which it can accurately automatically label unlabeled data…

Cited by 2SourcePDFScholar