SaR: Self-adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-supervised Learning
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 33, 4090-4099
Abstract
Class-imbalanced datasets can severely deteriorate the performance of semi-supervised learning (SSL). This is due to the confirmation bias especially when the pseudo labels are highly biased towards the majority classes. Traditional resampling or reweighting techniques may not be directly applicable when the unlabeled data distribution is unknown. Inspired by the threshold-moving method that performs well in supervised learning-based binary classification tasks, we provide a simple yet effective scheme to address the multiclass imbalance issue of SSL. This scheme, named SaR, is a Self-adaptive Refinement of soft labels before generating pseudo labels. The pseudo labels generated post-SaR will be less biased, resulting in higher quality data for training the classifier. We show that SaR can consistently improve recent consistency-based SSL algorithms on various image classification problems across different imbalanced ratios. We also show that SaR is robust to the situations where unlabeled data have different distributions as labeled data. Hence, SaR does not rely on the assumptions that unlabeled data share the same distribution as the labeled data.Keywords
This publication has 25 references indexed in Scilit:
- Learning from Imbalanced Data Sets with Weighted Cross-Entropy FunctionNeural Processing Letters, 2019
- A systematic study of the class imbalance problem in convolutional neural networksNeural Networks, 2018
- The iNaturalist Species Classification and Detection Dataset2018
- Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification2018
- A simple plug-in bagging ensemble based on threshold-moving for classifying binary and multiclass imbalanced dataNeurocomputing, 2018
- Semi-supervised AUC optimization based on positive-unlabeled learningMachine Learning, 2017
- A Survey of Predictive Modeling on Imbalanced DomainsACM Computing Surveys, 2016
- Learning Deep Representation for Imbalanced Classification2016
- Training cost-sensitive neural networks with methods addressing the class imbalance problemIEEE Transactions on Knowledge and Data Engineering, 2005
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002