Research map / Label-efficient and robust learning / Semi-supervised learning
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, Mubarak Shah
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| select pseudo-labels using confidence and prediction uncertainty (ablation) | pseudo-labeling on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 16.50 -> 8.14 | Improved |
| select pseudo-labels using confidence and prediction uncertainty (ablation) | pseudo-labeling on CIFAR-10 · CIFAR-10, 4000 labels | error rate (%): 10.02 -> 6.36 | Improved |
| add negative learning for selected negative pseudo-labels (ablation) | UPS on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 9.46 -> 8.14 | Improved |
| add negative learning for selected negative pseudo-labels (ablation) | UPS on CIFAR-10 · CIFAR-10, 4000 labels | error rate (%): 6.64 -> 6.36 | Improved |
| add confidence-based pseudo-label selection (ablation) | pseudo-labeling on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 22.60 -> 16.50 | Improved |
| add confidence-based pseudo-label selection (ablation) | pseudo-labeling on CIFAR-10 · CIFAR-10, 4000 labels | error rate (%): 12.94 -> 10.02 | Improved |
| add MC-Dropout calibration while retaining confidence selection (ablation) | UPS on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 16.50 -> 13.68 | Improved |
| add MC-Dropout calibration while retaining confidence selection (ablation) | UPS on CIFAR-10 · CIFAR-10, 4000 labels | error rate (%): 10.02 -> 8.09 | Improved |
| add Mixup augmentation without negative learning (ablation) | UPS on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 9.46 -> 7.30 | Improved |
| replace MC-Dropout uncertainty estimation with MC-SpatialDropout (ablation) | UPS on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 8.14 -> 8.28 | No clear effect |
| replace MC-Dropout uncertainty estimation with MC-DropBlock (ablation) | UPS on CIFAR-10 · CIFAR-10, 1000 labels | error rate (%): 8.14 -> 9.76 | Hurt |
| add class balancing during pseudo-label selection (ablation) | UPS · CIFAR-10, 1000 labels | accuracy: 88.77 -> 91.86 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MixMatch — MixMatch: A Holistic Approach to Semi-Supervised Learning (NeurIPS 2019) · better on 1 of 1 shared result
- DualStudent — Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning (ICCV 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels (NeurIPS 2025 · similarity 0.92)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.90)
- Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling (AAAI 2025 · similarity 0.90)
- Leveraging Local Variance for Pseudo-Label Selection in Semi-supervised Learning (AAAI 2024 · similarity 0.89)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
