Maximizing Unlabeled Data Utility With Improved Representation Learning and Pseudo Labeling
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 7, 1752-1764
Abstract
No abstract availableFunding Information
- U.S. Department of Energy (DE-FE0032196)
This publication has 30 references indexed in Scilit:
- A novel wavelet-transformer discriminator for semi-supervised GANs with controlled regularization and ensemble techniquesMultimedia Tools and Applications, 2025
- Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training2023
- TCC-net: A two-stage training method with contradictory loss and co-teaching based on meta-learning for learning with noisy labelsInformation Sciences, 2023
- Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning2022
- Exploring Simple Siamese Representation Learning2021
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Self-Training With Noisy Student Improves ImageNet Classification2020
- Meta-Learning With Differentiable Convex Optimization2019
- Label Propagation for Deep Semi-Supervised Learning2019
- AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Data2019