Research map / Label-efficient and robust learning / Recognition and long-tail
FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning
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 |
|---|---|---|---|
| Fusing refinement and disambiguation (FREDIS) instead of standard PLL-style methods | unreliable partial label learning · Fashion-MNIST, Kuzushiji-MNIST, CIFAR-10, CIFAR-100 (subset of settings) | test accuracy (%): e.g. 91.76 vs 90.97 (PLCR) on FMNIST γ1=0.1 γ2=0.5; 60.31 vs 52.99 (CC) on CIFAR-100 | Helped |
| Gap between FREDIS and baselines widens at higher unreliable levels | FREDIS vs PLCR · CIFAR-10 γ1=0.5 γ2=0.3 | test accuracy (%): 75.80 vs 68.59 (PLCR at γ1=0.5, γ2=0.5 is 68.59 ; FREDIS 75.80 at γ1=0.5 γ2=0.5 row) | Helped |
| Sensitivity of thresholds ζ0 and ζ̄0 (refinement/disambiguation initial thresholds) (ablation) | FREDIS · Fashion-MNIST and CIFAR-10 threshold sweep | test accuracy (%) | No clear effect |
Closest papers by meaning
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.91)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.90)
- Partial Label Learning with a Partner (AAAI 2024 · similarity 0.89)
- Controller-Guided Partial Label Consistency Regularization with Unlabeled Data (AAAI 2024 · similarity 0.89)
- ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision (ICML 2024 · similarity 0.88)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 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.