Research map / Label-efficient and robust learning / Noisy labels
Why Can Accurate Models Be Learned from Inaccurate Annotations?
Chongjie Si, Yidan Cui, Fuchao Yang, Wei Shen
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 |
|---|---|---|---|
| add PSP and LAP (full LIP) to PRODEN (ablation) | PRODEN · CIFAR-100 p=0.1 | accuracy: 76.04 -> 76.42 | Improved |
| add PSP and LAP (full LIP) to PRODEN (ablation) | PRODEN · CIFAR-100 p=0.05 | accuracy: 77.12 -> 77.25 | Improved |
| add PSP and LAP (full LIP) to PRODEN (ablation) | PRODEN · CIFAR-100 p=0.2 | accuracy: 56.83 -> 56.90 | Improved |
| add PSP and LAP (full LIP) to PRODEN (ablation) | PRODEN · CUB-200 p=0.06 | accuracy: 72.01 -> 72.33 | Improved |
| add PSP and LAP (full LIP) to PRODEN (ablation) | PRODEN · CUB-200 p=0.04 | accuracy: 74.36 -> 74.51 | Improved |
| add PSP and LAP (full LIP) to PRODEN (ablation) | PRODEN · CUB-200 p=0.02 | accuracy: 74.53 -> 74.73 | Improved |
| add LAP on top of PSP (ablation) | PRODEN + PSP · CUB-200 p=0.06 | accuracy: 72.17 -> 72.33 | Improved |
| add LAP on top of PSP (ablation) | PRODEN + PSP · CIFAR-100 p=0.1 | accuracy: 76.25 -> 76.42 | Improved |
Closest papers by meaning
- Collaborative Refining for Learning from Inaccurate Labels (NeurIPS 2024 · similarity 0.88)
- Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom (NeurIPS 2024 · similarity 0.87)
- Learning from Noisy Labels via Conditional Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.87)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.86)
- ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision (ICML 2024 · similarity 0.86)
- An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations (NeurIPS 2025 · similarity 0.86)
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.
