FocalMatch: Mitigating Class Imbalance of Pseudo Labels in Semi-Supervised Learning

FocalMatch: Mitigating Class Imbalance of Pseudo Labels in Semi-Supervised Learning

Semi-supervised learning (SSL) is a popular research area in machine learning which utilizes both labeled and unlabeled data. As an important method for the generation of artificial hard labels for unlabeled data, the pseudo-labeling method is introduced by applying a high and fixed threshold in mos...

Full description

Bibliographic Details
Main Authors: Yongkun Deng, Chenghao Zhang, Nan Yang, Huaming Chen
Format: Article
Language:English
Published: MDPI AG 2022-10-01
Series:Applied Sciences
Subjects:
semi-supervised learning
class imbalance
data privacy
Online Access:https://www.mdpi.com/2076-3417/12/20/10623

Similar Items

Similar Items