Research map / Label-efficient and robust learning / Noisy labels
Learning with Feature-Dependent Label Noise: A Progressive Approach
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 progressive confidence-based label correction and iterative retraining | CIFAR-10 and CIFAR-100 under feature-dependent noise · Type-I, Type-II, and Type-III noise at 35% and 70% | test accuracy | Helped |
| Use progressive confidence-based label correction and iterative retraining | PLC · CIFAR-10 and CIFAR-100 with hybrid feature-dependent and i.i.d. noise | test accuracy | Helped |
| Use progressive confidence-based label correction and iterative retraining | PLC · Clothing1M, Food-101N, and ANIMAL-10N | test accuracy | Helped |
| Vary the initial confidence threshold exp(θ₀) across 0.2, 0.3, 0.4, and 0.5 (ablation) | PLC · CIFAR-10, 35% feature-dependent noise | test accuracy: 83.33; 83.04; 82.66; 82.94 | No clear effect |
| Vary the threshold step size β across 0.05, 0.1, 0.2, and 0.3 (ablation) | PLC · CIFAR-10, 35% feature-dependent noise | test accuracy: 83.58; 83.04; 83.28; 83.31 | No clear effect |
Closest papers by meaning
- Correlated Input-Dependent Label Noise in Large-Scale Image Classification (CVPR 2021 · similarity 0.91)
- Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise (AAAI 2021 · similarity 0.90)
- On the Role of Label Noise in the Feature Learning Process (ICML 2025 · similarity 0.89)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.89)
- NoiseGPT: Label Noise Detection and Rectification through Probability Curvature (NeurIPS 2024 · similarity 0.89)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 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.