Research map / Label-efficient and robust learning / Noisy labels
Noise-Robust Learning from Multiple Unsupervised Sources of Inferred Labels
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 MULTI-IDNC plus MULTI-CCNC with multiple inferred-label sources | Our Approach · Amazon MR, 20NG, SearchSnippet, CIFAR10, CIFAR20, STL10, Cora, Citeseer, Pubmed | Accuracy: 6.4% in accuracy | Helped |
| Add MULTI-IDNC for instance-dependent noise correction (ablation) | Our Approach · Amazon MR, 20NG, SearchSnippet, CIFAR10, CIFAR20, STL10, Cora, Citeseer, Pubmed | Accuracy | Helped |
| Add MULTI-CCNC for class-conditional noise correction (ablation) | Our Approach · Amazon MR, 20NG, SearchSnippet, CIFAR10, CIFAR20, STL10, Cora, Citeseer, Pubmed | Accuracy | Helped |
| Balance the three MULTI-IDNC loss terms using β around 0.5 (ablation) | MULTI-IDNC · DI, DIII, DIV | Accuracy | Helped |
| Use the full MULTI-IDNC + MULTI-CCNC model rather than MULTI-CCNC alone on sources containing only class-conditional noise (ablation) | Our Approach · Amazon MR synthetic symmetric-noise experiment | Accuracy: 0.8% | Hurt |
Closest papers by meaning
- Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model (AAAI 2021 · similarity 0.93)
- A Second-Order Approach to Learning With Instance-Dependent Label Noise (CVPR 2021 · similarity 0.91)
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR 2021 · similarity 0.91)
- Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach (CVPR 2017 · similarity 0.91)
- Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks (NeurIPS 2017 · similarity 0.90)
- On the Role of Label Noise in the Feature Learning Process (ICML 2025 · similarity 0.89)
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.