InstanT: Semi-supervised Learning with Instance-dependent Thresholds

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves assigning pseudo-labels to confident unlabeled instances and incorporating them into the training set.

Data and Resources

Cite this as

Muyang Li, Runze Wu, Haoyu Liu, Jun Yu, Xun Yang, Bo Han, Tongliang Liu (2024). Dataset: InstanT: Semi-supervised Learning with Instance-dependent Thresholds. https://doi.org/10.57702/y188bq0o

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2310.18910
Author Muyang Li
More Authors
Runze Wu
Haoyu Liu
Jun Yu
Xun Yang
Bo Han
Tongliang Liu
Homepage https://github.com/tmllab/2023_NeurIPS_InstanT