"DC-SSL: Addressing Mismatched Class Distribution in Semi-supervised Le" by Zhen Zhao, Luping Zhou et al.
Consistency-based Semi-supervised learning (SSL) has achieved promising performance recently. However, the success largely depends on the assumption that the labeled and unlabeled data share an identical class distribution, which is hard to meet in real practice. The distribution mismatch between the labeled and unlabeled sets can cause severe bias in the pseudo-labels of SSL, resulting in significant performance degradation. To bridge this gap, we put forward a new SSL learning framework, named...
Distribution Consistency Exponentially Moving Average Machine Learning Elf Semi Meta Efficient Learning And Inferences
Source: uow.edu.au