Twice Class Bias Correction for Imbalanced Semi-supervised Learning
DOI:
https://doi.org/10.1609/aaai.v38i12.29260Keywords:
ML: Semi-Supervised Learning, ML: Classification and RegressionAbstract
Differing from traditional semi-supervised learning, class-imbalanced semi-supervised learning presents two distinct challenges: (1) The imbalanced distribution of training samples leads to model bias towards certain classes, and (2) the distribution of unlabeled samples is unknown and potentially distinct from that of labeled samples, which further contributes to class bias in the pseudo-labels during the training. To address these dual challenges, we introduce a novel approach called Twice Class Bias Correction (TCBC). We begin by utilizing an estimate of the class distribution from the participating training samples to correct the model, enabling it to learn the posterior probabilities of samples under a class-balanced prior. This correction serves to alleviate the inherent class bias of the model. Building upon this foundation, we further estimate the class bias of the current model parameters during the training process. We apply a secondary correction to the model's pseudo-labels for unlabeled samples, aiming to make the assignment of pseudo-labels across different classes of unlabeled samples as equitable as possible. Through extensive experimentation on CIFAR10/100-LT, STL10-LT, and the sizable long-tailed dataset SUN397, we provide conclusive evidence that our proposed TCBC method reliably enhances the performance of class-imbalanced semi-supervised learning.Downloads
Published
2024-03-24
How to Cite
Li, L., Tao, B., Han, L., Zhan, D.- chuan, & Ye, H.- jia. (2024). Twice Class Bias Correction for Imbalanced Semi-supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(12), 13563-13571. https://doi.org/10.1609/aaai.v38i12.29260
Issue
Section
AAAI Technical Track on Machine Learning III