Research map / Label-efficient and robust learning / Noisy labels
Uncertainty-Aware Learning against Label Noise on Imbalanced Datasets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use class-specific rather than class-agnostic noise modeling (ablation) | ULC · Imbalanced CIFAR-10, 1:10 resampling, symmetric 20% noise | best test accuracy (%): 82.5 -> 93.8 | Helped |
| Use epistemic uncertainty-aware noise modeling (ablation) | ULC · Imbalanced CIFAR-10, 1:10 resampling, symmetric 20% noise | best test accuracy (%): 90.7 -> 93.8 | Helped |
| Use aleatoric uncertainty-aware learning (ablation) | ULC · Imbalanced CIFAR-10, 1:10 resampling, symmetric 20% noise | best test accuracy (%): 91.8 -> 93.8 | Helped |
| Use FixMatch instead of MixMatch for the SSL component | ULC · Clothing1M | test accuracy (%): 75.2$\pm$0.2% | Helped |
Closest papers by meaning
- Noise-Robust Learning from Multiple Unsupervised Sources of Inferred Labels (AAAI 2022 · similarity 0.90)
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization (NeurIPS 2025 · similarity 0.89)
- Learning Imbalanced Data with Beneficial Label Noise (ICML 2025 · similarity 0.89)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.88)
- Deep Active Learning with Noise Stability (AAAI 2024 · similarity 0.88)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · 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.